Skip to content

Conversational Intelligence

Anthropic
API integration

Ship Conversational Intelligence features without building the integration. Full Anthropic API access via Proxy, normalized data through Unified APIs, and 110+ MCP-ready tools for AI agents — all extensible to your exact use case.

Talk to us
Anthropic

Use Cases

Why integrate with Anthropic

Common scenarios for SaaS companies building Anthropic integrations for their customers.

01

Multi-Tenant AI Workspace Provisioning

SaaS platforms can automatically create and manage isolated Anthropic workspaces per customer, syncing their internal RBAC with Anthropic's workspace members to ensure data isolation, separate rate limits, and per-tenant billing attribution.

02

Cost-Controlled AI Feature Embedding

SaaS companies offering AI-powered features need to track and throttle token spend per customer to maintain unit economics. By pulling usage and cost reports segmented by workspace and API key, platforms can implement metered billing and spending guardrails for their end users.

03

Asynchronous Bulk Document Processing

Platforms handling high-volume document workflows — contract review, data enrichment, content generation — can leverage Anthropic's message batch and file APIs to process thousands of items overnight at reduced cost, delivering results to end users by morning.

04

Embedded Prompt Engineering for Non-Technical Users

SaaS products can surface Anthropic's prompt generation, improvement, and templatization capabilities directly in their UI, allowing end users to create production-quality prompts without AI expertise — reducing support burden and improving output consistency.

05

Unified User Directory Sync for AI Governance

Enterprise SaaS platforms need to keep their user directories in sync with Anthropic's organization members and workspace assignments. Truto's Unified User Directory API enables automated provisioning and deprovisioning as team members join or leave.

What You Can Build

Ship these features with Truto + Anthropic

Concrete product features your team can ship faster by leveraging Truto’s Anthropic integration instead of building from scratch.

01

Per-Customer AI Cost Dashboard

Pull message usage reports and cost reports by workspace and API key to build a real-time dashboard showing token consumption and spend per tenant, enabling usage-based billing pass-through.

02

Automated Workspace & Member Lifecycle Management

Automatically create Anthropic workspaces when new customers onboard, provision workspace members with appropriate roles, and archive workspaces or remove members on churn — all synced via Truto's Unified User Directory API.

03

Drag-and-Drop Document Intelligence Pipeline

Let end users upload PDFs and datasets via your UI, use the files API to pass them to Claude, and return structured extracted data like invoice line items, contract clauses, or compliance findings.

04

Overnight Batch Processing Engine

Queue thousands of message requests into Anthropic message batches, monitor batch status, and retrieve results asynchronously — ideal for bulk CRM enrichment, sentiment analysis, or content generation at discounted compute costs.

05

Self-Service Prompt Optimizer

Embed prompt improvement and templatization directly into your product so end users can paste a rough instruction and receive an optimized, parameterized prompt ready for automated workflows.

06

API Key & Organization Invite Management Console

Build an admin panel where customers can view their active API keys, manage organization invites, and audit workspace membership — all without leaving your application.

SuperAI

Anthropic AI agent tools

Comprehensive AI agent toolset with fine-grained control. Integrates with MCP clients like Cursor and Claude, or frameworks like LangChain.

list_all_anthropic_users

List users in Anthropic. Returns id, name, email, role, type, and added_at for each user. Also includes first_id, last_id, and has_more for pagination.

get_single_anthropic_user_by_id

Get details of a specific user in Anthropic. Requires id. Returns added_at (when user joined), email, id, name, role, and type (always 'user').

update_a_anthropic_user_by_id

Update user role in Anthropic. Requires id. Returns added_at (when user joined), email (user email), id (user identifier), name (user name), role (organization role), and type (always 'user').

delete_a_anthropic_user_by_id

Delete a user in Anthropic. Requires id. Returns id of the deleted user and type confirming deletion as user_deleted.

list_all_anthropic_workspaces

List workspaces in Anthropic. Returns id, name, display_color, created_at, archived_at, and type for each workspace, along with pagination fields first_id, last_id, and has_more.

get_single_anthropic_workspace_by_id

Get a workspace in Anthropic using id. Returns id, name, display_color, created_at, archived_at, and type fields in the response.

create_a_anthropic_workspace

Create a workspace in Anthropic. Requires name. Returns id, name, created_at, archived_at, display_color, and type fields in the response.

update_a_anthropic_workspace_by_id

Update a workspace in Anthropic using id. Returns archived_at (when workspace was archived), created_at (when workspace was created), display_color (workspace color in console), id (workspace identifier), name (workspace name), and type (always workspace).

anthropic_workspaces_archive

Archive a workspace in Anthropic. Requires id. Returns archived_at (when the workspace was archived), created_at, display_color, id, name, and type.

list_all_anthropic_workspace_members

List workspace_members in Anthropic. Requires workspace_id. Returns type, user_id, workspace_id, and workspace_role for each member along with pagination fields first_id, last_id, and has_more.

get_single_anthropic_workspace_member_by_id

Get a workspace member in Anthropic. Requires workspace_id and id. Returns type (always workspace_member), user_id (the user identifier), workspace_id (the workspace identifier), and workspace_role (member role).

create_a_anthropic_workspace_member

Create a workspace member in Anthropic. Requires workspace_id, user_id, and workspace_role. Returns type (always workspace_member), user_id, workspace_id, and workspace_role of the created member.

update_a_anthropic_workspace_member_by_id

Update a workspace member in Anthropic. Requires workspace_id and id. Returns type (always workspace_member), user_id, workspace_id, and workspace_role indicating the updated role.

delete_a_anthropic_workspace_member_by_id

Delete a specific workspace member in Anthropic. Requires workspace_id and id. Returns type confirming deletion as workspace_member_deleted, user_id of the member removed, and workspace_id where the deletion occurred.

list_all_anthropic_organization

Get details about the authenticated organization in Anthropic. Returns id (organization identifier), name (organization name), and type (always 'organization').

list_all_anthropic_organizations_invites

List invites in Anthropic. Returns id, email, invited_at, expires_at, role, status, and type for each invite. Also returns pagination fields first_id, last_id, and has_more.

get_single_anthropic_organizations_invite_by_id

Get a specific invite in Anthropic. Requires id. Returns email of invited user, role assigned, status of the invite, when it was created (invited_at), when it expires (expires_at), and type (always 'invite').

create_a_anthropic_organizations_invite

Create an invite in Anthropic. Requires email and role. Returns id, email, role, status, invited_at, expires_at, and type fields in the response.

delete_a_anthropic_organizations_invite_by_id

Delete an invite in Anthropic. Requires id. Returns id of the deleted invite and type confirming invite_deleted.

list_all_anthropic_api_keys

List API keys in Anthropic. Returns id, name, created_at, created_by, status, partial_key_hint, workspace_id, and type for each API key.

get_single_anthropic_api_key_by_id

Get details of a specific API key in Anthropic using id. Returns id, name, status, created_at, created_by, partial_key_hint, type, and workspace_id.

update_a_anthropic_api_key_by_id

Update an API key in Anthropic. Requires id. Returns created_at (creation time), created_by (actor details), id (API key identifier), name (API key name), partial_key_hint (redacted hint), status (active/inactive/archived), type (always api_key), and workspace_id (associated workspace).

list_all_anthropic_message_usage_report

Get message usage report in Anthropic. Requires starting_at. Returns time bucketed data with fields: starting_at, ending_at, uncached_input_tokens, cache_creation, cache_read_input_tokens, output_tokens, server_tool_use, api_key_id, workspace_id, model, service_tier, and context_window.

list_all_anthropic_cost_report

Get cost report in Anthropic. Requires starting_at. Returns time buckets with starting_at, ending_at, and results containing currency, amount, workspace_id, description, cost_type, context_window, model, service_tier, and token_type. Also returns has_more and next_page for pagination.

list_all_anthropic_claude_code_usage_report

Get the Claude Code usage report in Anthropic for a specific date using starting_at. Returns usage metrics including actor, core_metrics (commits, lines_of_code, sessions, pull_requests), model_breakdown with tokens and estimated_cost, organization_id, subscription_type, terminal_type, and tool_actions.

create_a_anthropic_generate_prompt

Generate a prompt in Anthropic by providing task. Returns messages containing generated prompt text for use with the Messages API, system placeholder, and usage details including input_tokens and output_tokens.

create_a_anthropic_improve_prompt

Create an improved prompt in Anthropic using messages as input. Returns messages containing the improved prompt text and optionally an assistant prefill, system as an empty string, and usage with input_tokens and output_tokens.

create_a_anthropic_templatize_prompt

Templatize a prompt in Anthropic by extracting variables from messages and system input. Returns messages with variables replaced, system prompt with placeholders, variable_values mapping original inputs, and usage with token counts.

create_a_anthropic_message

Create a new message in Anthropic. Requires model, messages, and max_tokens. Returns id (unique identifier), role (assistant), content (generated text or tool use), model, stop_reason, stop_sequence, usage (token counts), and container details.

anthropic_messages_count_tokens

Count tokens in messages in Anthropic. Requires messages and model. Returns input_tokens representing the total number of tokens across messages, system prompt, and tools.

list_all_anthropic_models

List available models in Anthropic. Returns id (unique model identifier), display_name (human-readable name), created_at (release time), and type (always 'model').

get_single_anthropic_model_by_id

Get a specific model in Anthropic using id. Returns created_at (release date), display_name (human-readable name), id (model identifier), and type (always 'model').

list_all_anthropic_message_batches

List all message batches in Anthropic. Returns id, created_at, processing_status, request_counts, results_url, and timing fields for each batch. Batches are returned with the most recently created first.

get_single_anthropic_message_batch_by_id

Get details of a specific message-batch in Anthropic using id. Returns timestamps (created_at, ended_at, expires_at, archived_at, cancel_initiated_at), processing_status, request_counts for requests, results_url to fetch processed results, and type.

create_a_anthropic_message_batch

Create a Message Batch in Anthropic. Requires requests array with individual message request parameters. Returns id, created_at, processing_status, request_counts, results_url, and other timestamps for tracking batch processing.

delete_a_anthropic_message_batch_by_id

Delete a specific message-batch in Anthropic. Requires id. Only finished batches can be deleted; in-progress batches must be canceled first. Returns id of the deleted batch and type confirming deletion.

anthropic_message_batches_cancel

Cancel a message batch in Anthropic. Requires id. Returns id, processing_status, request_counts with tallies of canceled, succeeded, errored, expired, and processing requests, along with created_at, cancel_initiated_at, ended_at, expires_at, archived_at, results_url, and type. Cancellation is only effective before processing ends, and non-interruptible requests may still complete.

anthropic_message_batches_results

Get results of a specific message-batch in Anthropic. Requires id. Response returns each request's custom_id and result, where result can include a succeeded message with fields such as content, model, usage, and stop_reason, or error/cancellation details.

list_all_anthropic_files

List files in Anthropic. Returns created_at (creation time), id (file identifier), filename, mime_type, size_bytes, type (always 'file'), and downloadable status for each file.

get_single_anthropic_file_by_id

Get metadata for a specific file in Anthropic using id. Returns created_at (file creation time), filename (original uploaded name), id (unique identifier), mime_type (file type), size_bytes (file size), downloadable (if file can be retrieved), and type (always 'file').

create_a_anthropic_file

Create a file in Anthropic by uploading a binary file. Requires a multipart form-data request with file. Returns id, filename, mime_type, size_bytes, created_at, type, and whether the file is downloadable.

delete_a_anthropic_file_by_id

Delete a file in Anthropic by id. Returns id of the deleted file and type confirming deletion (file_deleted).

anthropic_files_download

Download the contents of a specific file in Anthropic. Requires id. Returns the raw file content as binary data.

list_all_anthropic_agents

List Anthropic managed agents in the workspace. Returns a list of agent objects, each including id, name, archived_at, created_at, description, mcp_servers, metadata, model, multiagent, skills, system, tools, and other fields.

get_single_anthropic_agent_by_id

Get a managed agent by id. Pass the optional version query param to fetch a specific saved version. Returns the agent including id, name, archived_at, created_at, description, mcp_servers, metadata, model, multiagent, skills, system, tools, and other fields. Required: id.

create_a_anthropic_agent

Create a managed agent. The model and name are required; system prompt, tools, skills, MCP servers, multiagent roster and metadata are optional. Returns the agent including id, name, archived_at, created_at, description, mcp_servers, metadata, model, multiagent, skills, system, tools, and other fields. Required: model, name.

update_a_anthropic_agent_by_id

Update a managed agent by id. Send only the fields to change; pass the agent's current version to guard against concurrent overwrites. Returns the agent including id, name, archived_at, created_at, description, mcp_servers, metadata, model, multiagent, skills, system, tools, and other fields. Required: id.

anthropic_agents_archive

Archive a managed agent by agent_id so it can no longer be used to start new sessions. Returns the agent including id, name, archived_at, created_at, description, mcp_servers, metadata, model, multiagent, skills, system, tools, and other fields. Required: agent_id.

list_all_anthropic_agent_versions

List the saved versions of a managed agent. Returns a list of agent version objects, each including id, name, archived_at, created_at, description, mcp_servers, metadata, model, multiagent, skills, system, tools, and other fields. Required: agent_id.

list_all_anthropic_environments

List Anthropic environments (the container configurations sessions run in). Returns a list of environment objects, each including id, name, archived_at, config, created_at, description, metadata, updated_at, and scope.

get_single_anthropic_environment_by_id

Get an environment by id. Returns the environment including id, name, archived_at, config, created_at, description, metadata, updated_at, and scope. Required: id.

create_a_anthropic_environment

Create an environment that defines the container configuration (networking, packages) for sessions. The name is required. Returns the environment including id, name, archived_at, config, created_at, description, metadata, updated_at, and scope. Required: name.

update_a_anthropic_environment_by_id

Update an environment by id (name, description, config, metadata or scope). Returns the environment including id, name, archived_at, config, created_at, description, metadata, updated_at, and scope. Required: id.

delete_a_anthropic_environment_by_id

Delete an environment by id. Returns a deletion confirmation with id and type. Required: id.

anthropic_environments_archive

Archive an environment by environment_id so it can no longer be used to create new sessions. Returns the environment including id, name, archived_at, config, created_at, description, metadata, updated_at, and scope. Required: environment_id.

list_all_anthropic_sessions

List managed-agent sessions, newest first by default. Filter by agent, agent version, deployment, memory store, status or archived state. Returns a list of session objects, each including id, title, status, agent, archived_at, budget, created_at, environment_id, metadata, outcome_evaluations, resources, stats, and other fields.

get_single_anthropic_session_by_id

Get a managed-agent session by id, including its status, agent snapshot, resources, usage and stats. Returns the session including id, title, status, agent, archived_at, budget, created_at, environment_id, metadata, outcome_evaluations, resources, stats, and other fields. Required: id.

create_a_anthropic_session

Create a managed-agent session that runs an agent inside an environment. The agent (an agent ID string or an object with id and version) and environment_id are required; vault_ids, resources, initial_events, budget, title and metadata are optional. Returns the session including id, title, status, agent, archived_at, budget, created_at, environment_id, metadata, outcome_evaluations, resources, stats, and other fields. Required: agent, environment_id.

update_a_anthropic_session_by_id

Update a session by id: its title, metadata, budget, attached tools and MCP servers (agent), or vault_ids. The session must not be running when agent is changed. Returns the session including id, title, status, agent, archived_at, budget, created_at, environment_id, metadata, outcome_evaluations, resources, stats, and other fields. Required: id.

delete_a_anthropic_session_by_id

Permanently delete a session by id. Returns a deletion confirmation with id and type. Required: id.

anthropic_sessions_archive

Archive a session by session_id. Returns the session including id, title, status, agent, archived_at, budget, created_at, environment_id, metadata, outcome_evaluations, resources, stats, and other fields. Required: session_id.

list_all_anthropic_session_events

List the events of a session in processed_at order. Filter by event types or created_at. Returns events, each with id, type and processed_at plus type-specific fields such as content. Required: session_id.

create_a_anthropic_session_event

Send events to a session. The events array is required; each event has a type (user.message, user.interrupt, user.tool_confirmation, user.custom_tool_result, user.tool_result, user.define_outcome or system.message) plus that type's fields, such as content for user.message. Returns a data array of the resulting session events. Required: session_id, events.

list_all_anthropic_session_resources

List the resources (files, GitHub repositories, memory stores) mounted into a session. Returns a list of session resource objects, each including id, name, created_at, mount_path, updated_at, url, checkout, file_id, memory_store_id, access, description, and instructions. Required: session_id.

get_single_anthropic_session_resource_by_id

Get a session resource by id. Returns the session resource including id, name, created_at, mount_path, updated_at, url, checkout, file_id, memory_store_id, access, description, and instructions. Required: session_id, id.

create_a_anthropic_session_resource

Add a file resource to a session. The file_id of a previously uploaded file and type "file" are required; mount_path is optional. Returns the session resource including id, created_at, file_id, mount_path, and updated_at. Required: session_id, file_id, type.

update_a_anthropic_session_resource_by_id

Rotate the authorization token of a session resource (currently only github_repository resources support this). The authorization_token is required. Returns the session resource including id, name, created_at, mount_path, updated_at, url, checkout, file_id, memory_store_id, access, description, and instructions. Required: session_id, id, authorization_token.

delete_a_anthropic_session_resource_by_id

Remove a resource from a session by id. Returns a deletion confirmation with id and type. Required: session_id, id.

list_all_anthropic_session_threads

List the threads of a multi-agent session. Returns a list of session thread objects, each including id, status, agent, archived_at, created_at, parent_thread_id, session_id, stats, updated_at, and usage. Required: session_id.

get_single_anthropic_session_thread_by_id

Get a session thread by id. Returns the session thread including id, status, agent, archived_at, created_at, parent_thread_id, session_id, stats, updated_at, and usage. Required: session_id, id.

anthropic_session_threads_archive

Archive a session thread so it accepts no further input. Returns the session thread including id, status, agent, archived_at, created_at, parent_thread_id, session_id, stats, updated_at, and usage. Required: session_id, thread_id.

list_all_anthropic_session_thread_events

List the events of one thread within a session. Returns events, each with id, type and processed_at plus type-specific fields such as content. Required: session_id, thread_id.

list_all_anthropic_vaults

List Anthropic vaults, which store credentials agents can use during sessions. Optionally include archived vaults. Returns a list of vault objects, each including id, display_name, archived_at, created_at, metadata, and updated_at.

get_single_anthropic_vault_by_id

Get a vault by id. Returns the vault including id, display_name, archived_at, created_at, metadata, and updated_at. Required: id.

create_a_anthropic_vault

Create a vault for storing credentials used by agents during sessions. The display_name is required. Returns the vault including id, display_name, archived_at, created_at, metadata, and updated_at. Required: display_name.

update_a_anthropic_vault_by_id

Update a vault's display_name or metadata by id. Returns the vault including id, display_name, archived_at, created_at, metadata, and updated_at. Required: id.

delete_a_anthropic_vault_by_id

Delete a vault by id. Returns a deletion confirmation with id and type. Required: id.

anthropic_vaults_archive

Archive a vault by vault_id. Returns the vault including id, display_name, archived_at, created_at, metadata, and updated_at. Required: vault_id.

list_all_anthropic_vault_credentials

List the credentials stored in a vault. Optionally include archived credentials. Returns a list of credential objects, each including id, display_name, archived_at, auth, created_at, metadata, updated_at, and vault_id. Required: vault_id.

get_single_anthropic_vault_credential_by_id

Get a credential from a vault by id. Returns the credential including id, display_name, archived_at, auth, created_at, metadata, updated_at, and vault_id. Required: vault_id, id.

create_a_anthropic_vault_credential

Create a credential in a vault. The auth object is required and is one of mcp_oauth, static_bearer or environment_variable. Returns the credential including id, display_name, archived_at, auth, created_at, metadata, updated_at, and vault_id. Required: vault_id, auth.

update_a_anthropic_vault_credential_by_id

Update a vault credential by id (auth, display_name or metadata). The auth type is immutable: the variant sent must match the stored credential type. Returns the credential including id, display_name, archived_at, auth, created_at, metadata, updated_at, and vault_id. Required: vault_id, id.

delete_a_anthropic_vault_credential_by_id

Delete a credential from a vault by id. Returns a deletion confirmation with id and type. Required: vault_id, id.

anthropic_vault_credentials_archive

Archive a vault credential by credential_id. Returns the credential including id, display_name, archived_at, auth, created_at, metadata, updated_at, and vault_id. Required: vault_id, credential_id.

anthropic_vault_credentials_verify

Validate an MCP OAuth credential by probing its MCP server and refreshing the OAuth token if needed. Returns the credential validation including status, credential_id, has_refresh_token, mcp_probe, refresh, validated_at, and vault_id. Required: vault_id, credential_id.

list_all_anthropic_memory_stores

List memory stores. Optionally include archived stores or filter by created_at. Returns a list of memory store objects, each including id, name, archived_at, created_at, description, metadata, and updated_at.

get_single_anthropic_memory_store_by_id

Get a memory store by id. Returns the memory store including id, name, archived_at, created_at, description, metadata, and updated_at. Required: id.

create_a_anthropic_memory_store

Create a memory store, a named collection of memories agents can read and write. The name is required. Returns the memory store including id, name, archived_at, created_at, description, metadata, and updated_at. Required: name.

update_a_anthropic_memory_store_by_id

Update a memory store's name, description or metadata by id. Archived stores cannot be updated. Returns the memory store including id, name, archived_at, created_at, description, metadata, and updated_at. Required: id.

delete_a_anthropic_memory_store_by_id

Permanently delete a memory store by id, including all of its memories and memory versions. Returns a deletion confirmation with id and type. Required: id.

anthropic_memory_stores_archive

Archive a memory store by memory_store_id. Archiving is one-way; archived stores cannot be unarchived. Returns the memory store including id, name, archived_at, created_at, description, metadata, and updated_at. Required: memory_store_id.

list_all_anthropic_memories

List the memories in a memory store. Filter with path_prefix and depth; set view=full to include content. Returns memory items (id, type, path, content_sha256, content_size_bytes, memory_store_id, memory_version_id, created_at, updated_at, and content when view=full) and memory_prefix rollups when depth=1. Required: memory_store_id.

get_single_anthropic_memory_by_id

Get a memory by id from a memory store. Set view=full to include content. Returns the memory including id, content_sha256, content_size_bytes, created_at, memory_store_id, memory_version_id, path, updated_at, and content. Required: memory_store_id, id.

create_a_anthropic_memory

Create a memory in a memory store. The path and content are required. Returns the memory including id, content_sha256, content_size_bytes, created_at, memory_store_id, memory_version_id, path, updated_at, and content. Required: memory_store_id, content, path.

update_a_anthropic_memory_by_id

Update a memory by id: change its content, rename it with path, or both. Use precondition to apply the update only if the stored content_sha256 still matches. Returns the memory including id, content_sha256, content_size_bytes, created_at, memory_store_id, memory_version_id, path, updated_at, and content. Required: memory_store_id, id.

delete_a_anthropic_memory_by_id

Delete a memory by id from a memory store. Optionally pass expected_content_sha256 to delete only if the content is unchanged. Returns a deletion confirmation with id and type. Required: memory_store_id, id.

list_all_anthropic_memory_versions

List the version history of memories in a memory store. Filter by memory_id, operation, session_id, api_key_id, service_account_id or created_at. Returns a list of memory version objects, each including id, created_at, memory_id, memory_store_id, operation, content, content_sha256, content_size_bytes, created_by, path, redacted_at, and redacted_by. Required: memory_store_id.

get_single_anthropic_memory_version_by_id

Get a memory version by id. Set view=full to include content. Returns the memory version including id, created_at, memory_id, memory_store_id, operation, content, content_sha256, content_size_bytes, created_by, path, redacted_at, and redacted_by. Required: memory_store_id, id.

anthropic_memory_versions_redact

Redact a memory version, clearing its stored content (redacted_at and redacted_by record when and by whom). Returns the memory version including id, created_at, memory_id, memory_store_id, operation, content, content_sha256, content_size_bytes, created_by, path, redacted_at, and redacted_by. Required: memory_store_id, memory_version_id.

list_all_anthropic_deployments

List deployments, which run an agent in an environment on a schedule or on demand. Filter by agent_id, status or archived state. Returns a list of deployment objects, each including id, name, status, agent, archived_at, created_at, description, environment_id, initial_events, metadata, paused_reason, resources, and other fields.

get_single_anthropic_deployment_by_id

Get a deployment by id. Returns the deployment including id, name, status, agent, archived_at, created_at, description, environment_id, initial_events, metadata, paused_reason, resources, and other fields. Required: id.

create_a_anthropic_deployment

Create a deployment that starts sessions of an agent. The agent, environment_id, initial_events and name are required; schedule, resources, vault_ids and budget are optional. Returns the deployment including id, name, status, agent, archived_at, created_at, description, environment_id, initial_events, metadata, paused_reason, resources, and other fields. Required: agent, environment_id, initial_events, name.

update_a_anthropic_deployment_by_id

Update a deployment by id. Omitted fields are preserved; schedule, budget, resources and vault_ids are replaced as a whole when sent. Returns the deployment including id, name, status, agent, archived_at, created_at, description, environment_id, initial_events, metadata, paused_reason, resources, and other fields. Required: id.

anthropic_deployments_pause

Pause a deployment by deployment_id so its schedule stops firing. Returns the deployment including id, name, status, agent, archived_at, created_at, description, environment_id, initial_events, metadata, paused_reason, resources, and other fields. Required: deployment_id.

anthropic_deployments_resume

Unpause a paused deployment by deployment_id so its schedule fires again. Returns the deployment including id, name, status, agent, archived_at, created_at, description, environment_id, initial_events, metadata, paused_reason, resources, and other fields. Required: deployment_id.

anthropic_deployments_trigger

Run a deployment immediately by deployment_id, creating a session outside its schedule. Returns the deployment run including id, agent, created_at, deployment_id, error, session_id, and trigger_context. Required: deployment_id.

anthropic_deployments_archive

Archive a deployment by deployment_id so it can no longer run. Returns the deployment including id, name, status, agent, archived_at, created_at, description, environment_id, initial_events, metadata, paused_reason, resources, and other fields. Required: deployment_id.

list_all_anthropic_deployment_runs

List deployment runs. Filter by deployment_id, trigger_type or has_error, or by created_at. Returns a list of deployment run objects, each including id, agent, created_at, deployment_id, error, session_id, and trigger_context.

get_single_anthropic_deployment_run_by_id

Get a deployment run by id. Returns the deployment run including id, agent, created_at, deployment_id, error, session_id, and trigger_context. Required: id.

list_all_anthropic_skills

List Anthropic skills in the workspace. Optionally filter by source. Returns a list of skill objects, each including id, display_name, created_at, latest_version_id, source, and updated_at.

get_single_anthropic_skill_by_id

Get a skill by id. Returns the skill including id, display_name, created_at, latest_version_id, source, and updated_at. Required: id.

create_a_anthropic_skill

Create a skill by uploading its files as multipart/form-data. Optionally set display_name. Returns the skill including id, display_name, created_at, latest_version_id, source, and updated_at. Required: files.

delete_a_anthropic_skill_by_id

Delete a skill by id. Returns a deletion confirmation with id and type. Required: id.

list_all_anthropic_skill_versions

List the versions of a skill. Returns a list of skill version objects, each including id, name, created_at, description, and skill_id. Required: skill_id.

get_single_anthropic_skill_version_by_id

Get a skill version by id. Pass the literal id "latest" to get the most recent version. Returns the skill version including id, name, created_at, description, and skill_id. Required: skill_id, id.

create_a_anthropic_skill_version

Create a new version of a skill by uploading its files as multipart/form-data. Returns the skill version including id, name, created_at, description, and skill_id. Required: skill_id, files.

delete_a_anthropic_skill_version_by_id

Delete a skill version by id. Returns a deletion confirmation with id and type. Required: skill_id, id.

Why Truto

Why use Truto’s MCP server for Anthropic

Other MCP servers give you a static tool list for one app. Truto gives you a managed, multi-tenant MCP infrastructure across 850+ integrations.

01

Auto-generated, always up to date

Tools are dynamically generated from curated documentation — not hand-coded. As integrations evolve, tools stay current without manual maintenance.

02

Fine-grained access control

Scope each MCP server to read-only, write-only, specific methods, or tagged tool groups. Expose only what your AI agent needs — nothing more.

03

Multi-tenant by design

Each MCP server is scoped to a single connected account with its own credentials. The URL itself is the auth token — no shared secrets, no credential leaking across tenants.

04

Works with every MCP client

Standard JSON-RPC 2.0 protocol. Paste the URL into Claude, ChatGPT, Cursor, or any MCP-compatible agent framework — tools are discovered automatically.

05

Built-in auth, rate limits, and error handling

Tool calls execute through Truto’s proxy layer with automatic OAuth refresh, rate-limit handling, and normalized error responses. No raw API plumbing in your agent.

06

Expiring and auditable servers

Create time-limited MCP servers for contractors or automated workflows. Optional dual-auth requires both the URL and a Truto API token for high-security environments.

For your product

Ship Anthropic tools in your product

Give the AI in your product access to each customer’s own Anthropic account, with one MCP server per connected account.

Rather talk it through? Book a demo

Elaichi

For your own team

Use Anthropic in ChatGPT or Claude yourself

Connect your company’s Anthropic once, then ask in the AI you already use, with exactly your own access.

From the team behind Truto · 14-day free trial

Unified APIs

Unified APIs for Anthropic

Skip writing code for every integration. Use Truto’s category-specific Unified APIs out of the box or customize the mappings with AI.

Unified User Directory API

Organizations

Organizations are the top level entity in the source application. Users are associated with an organization.

View Docs

Roles

The Role object represents a role of a User.

View Docs

Users

The User object represents a User.

View Docs

Workspaces

Workspaces represent concepts like teams, workspaces, projects in apps that support them

View Docs

How It Works

From zero to integrated

Go live with Anthropic in under an hour. No boilerplate, no maintenance burden.

01

Link your customer’s Anthropic account

Use Truto’s frontend SDK to connect your customer’s Anthropic account. We handle all OAuth and API key flows — you don’t need to create the OAuth app.

02

We handle authentication

Don’t spend time refreshing access tokens or figuring out secure storage. We handle it and inject credentials into every API request.

03

Call our API, we call Anthropic

Truto’s Proxy API is a 1-to-1 mapping of the Anthropic API. You call us, we call Anthropic, and pass the response back in the same cycle.

04

Unified response format

Every response follows a single format across all integrations. We translate Anthropic’s pagination into unified cursor-based pagination. Data is always in the result attribute.

FAQs

Common questions about Anthropic on Truto

Authentication, rate limits, data freshness, and everything else you need to know before you integrate.

What authentication method does the Anthropic integration use?

Anthropic uses API key-based authentication. End users connect their Anthropic account by providing their API key through Truto, which securely manages the credential for all subsequent API calls.

Can I track AI costs per customer or workspace?

Yes. The integration supports listing message usage reports, cost reports, and Claude Code usage reports. These can be segmented by workspace ID and API key ID, enabling precise per-tenant cost attribution and billing pass-through.

What Unified APIs does this integration support?

The Anthropic integration maps to Truto's Unified User Directory API, covering Users (list, get, update, delete), Workspaces (list, get, create, update, archive), and Workspace Members (full CRUD with role management).

Does the integration support batch message processing?

Yes. You can create message batches, check their status, retrieve results, and cancel in-progress batches. This is ideal for high-volume async workloads like bulk document analysis or data enrichment at reduced cost.

Can I manage files through this integration?

Yes. The integration supports listing, uploading, retrieving, deleting, and downloading files via Anthropic's Files API. This enables document-to-data pipelines where end users upload files that are then processed by Claude.

What prompt engineering capabilities are available?

The integration exposes three prompt management endpoints: generate a prompt from a description, improve an existing prompt for better quality, and templatize a prompt with variables for reuse in automated workflows.

Anthropic

Get Anthropic integrated into your app

Our team understands what it takes to make a Anthropic integration successful. A short, crisp 30 minute call with folks who understand the problem.