Twenty MCP
Documentation — Installation, deployment, usage across the MCP, API, and agent interfaces, and guidance for provisioning the Twenty CRM platform are maintained in the official documentation.
Twenty CRM Customer Relationship Management system orchestrator. Built with the highest architectural standards, incorporating dynamic facades, custom API routing, and FastMCP tool decoration.
Table of Contents
- Overview
- Features
- Installation
- Usage
- Configuration
- MCP Tools
- Architecture
- Deployment
- Contributing
- License
Overview
Twenty MCP provides a high-performance, model-optimized interface to Twenty capabilities. It isolates the model from underlying API transport complexity, ensuring safe, idempotent, and highly traceable system interactions.
Features
- Dynamic Facade Orchestration: Integrates multi-inheritance clients cleanly under a single facade.
- Battle-Tested Resilience: Out-of-the-box credential authentication, connection polling, and request retry strategies.
- FastMCP Declarative Tools: Fast, native schema registration with full inline validation.
- Complete Test Intent Diversity: Deep, automated unit, integration, and mock tests ensuring high code coverage.
⚙️ Dynamic Tool Selection & Visibility
This MCP server supports dynamic toolset selection and visibility filtering at runtime. This allows the operator to restrict the set of exposed tools to prevent blowing up the LLM's context window.
The operator can configure tool filtering via multiple input channels:
- CLI Arguments: Pass
--toolsor--toolsets(or their disabled counterparts--disabled-toolsand--disabled-toolsets) during startup. - Environment Variables: Define standard environment variables:
MCP_ENABLED_TOOLS/MCP_DISABLED_TOOLSMCP_ENABLED_TAGS/MCP_DISABLED_TAGS
- HTTP SSE Request Headers: Pass custom headers during transport initialization:
x-mcp-enabled-tools/x-mcp-disabled-toolsx-mcp-enabled-tags/x-mcp-disabled-tags
- HTTP SSE Request Query Parameters: Append query parameters directly to the operator's transport connection URL:
?tools=tool1,tool2?tags=tag1
When query strings or parameters are provided, an LLM-free Knowledge Graph resolution layer (using DynamicToolOrchestrator) matches query intents against known tool tags, names, or descriptions, with safe fallback and automated 24-hour background cache refreshing.
Installation
Install the connector-focused
[mcp]extra. Examples usetwenty-mcp[mcp]to add FastMCP / FastAPI throughagent-connector-sdk; the required Agent Connector SDK core enables model orchestration.
Pick the extra that matches what the operator want to run:
| Extra | Installs | Use when |
|---|---|---|
twenty-mcp[mcp] |
Connector-focused MCP server (agent-connector-sdk — FastMCP/FastAPI + epistemic-graph[full]) |
The operator only run the MCP server (smallest install / image) |
twenty-mcp[all] |
Everything (mcp + agent + logfire + gql) |
Development / both surfaces |
# Connector-focused MCP server (includes the shared graph engine)
uv pip install "twenty-mcp[mcp]"
# Agent runtime (adds model orchestration to the shared graph engine)
# Everything (development)
uv pip install "twenty-mcp[all]" # or: python -m pip install "twenty-mcp[all]"
Container images (:mcp)
One multi-stage docker/Dockerfile builds the MCP-only image (--target mcp):
| Image tag | Build target | Contents | Entrypoint |
|---|---|---|---|
example/twenty-mcp:mcp |
--target mcp |
twenty-mcp[mcp] — connector-focused, includes epistemic-graph[full]; no model-orchestration stack |
twenty-mcp |
docker build --target mcp -t example/twenty-mcp:mcp docker/ # connector-focused MCP server
Knowledge-graph database (epistemic-graph)
Agent Connector SDK core dependency (epistemic-graph[full]). The [mcp] extra keeps
deployments can use the bundled engine. For production or shared state, run
epistemic-graph as a dedicated database service and configure the runtime to use it.
Deployment recipes (single-node + Raft HA), connection configuration, and architecture
diagrams are documented in the
epistemic-graph deployment guide.
Usage
The operator can start the FastMCP server in stdio mode via Python module execution:
import asyncio
from twenty_mcp.mcp_server import get_mcp_instance
async def main():
mcp = get_mcp_instance()
# Execute stdio loop or launch server
print("MCP Server ready.")
if __name__ == "__main__":
asyncio.run(main())
For direct shell start, run:
python -m twenty_mcp.mcp_server
Configuration
The package is fully configurable via the environment variables listed below. A local
template is provided inside .env.example — copy it to .env and fill in
the operator's service endpoint parameters before starting execution.
Connection & credentials
| Variable | Description | Default |
|---|---|---|
TWENTY_URL |
Twenty CRM Base Server URL | http://localhost:3000 |
TWENTY_TOKEN |
Developer authentication token | — |
TWENTY_MCP_BASE_URL |
Base API URL to query | http://localhost:3000/api |
TWENTY_API_PREFIX |
Twenty API custom path prefix | http://localhost:3000/api/v1 |
TWENTY_MCP_USERNAME |
Auth username for service | admin |
TWENTY_MCP_PASSWORD |
Auth password for service | — |
TWENTY_TLS_PROFILE |
Named outbound TLS policy from AgentConfig | system |
MCP server / transport
| Variable | Description | Default |
|---|---|---|
TRANSPORT |
stdio, streamable-http, or sse |
stdio |
HOST |
Bind host (HTTP transports) | 0.0.0.0 |
PORT |
Bind port (HTTP transports) | 8000 |
MCP_TOOL_MODE |
Tool surface: condensed, verbose, or both |
condensed |
MCP_ENABLED_TOOLS / MCP_DISABLED_TOOLS |
Comma-separated tool allow/deny list | — |
MCP_ENABLED_TAGS / MCP_DISABLED_TAGS |
Comma-separated tag allow/deny list | — |
Tool toggles
Each action-routed tool can be disabled individually via its toggle env var (set to false).
The full list is in the MCP Tools table below
(CRMTOOL, METADATATOOL, OAUTHTOOL, GRAPHQLTOOL).
Agent runtime (full [agent] runtime only)
| Variable | Description | Default |
|---|---|---|
MCP_URL |
URL of the MCP server the agent connects to | http://localhost:8000/mcp |
PROVIDER |
LLM provider (e.g. openai) |
openai |
MODEL_ID |
Model id (e.g. gpt-4o) |
gpt-4o |
MCP Tools
Auto-generated from the live MCP server — do not edit by hand.
Condensed action-routed tools (default — MCP_TOOL_MODE=condensed)
| MCP Tool | Toggle Env Var | Description |
|---|---|---|
twenty_discover_graphql_schema |
GRAPHQLTOOL |
Discover Twenty's underlying object/field/relation metadata (meta-model). |
twenty_graphql |
GRAPHQLTOOL |
Execute raw GraphQL queries and mutations natively on Twenty. |
twenty_mcp_crm |
CRMTOOL |
Manage Twenty MCP crm operations. |
twenty_mcp_metadata |
METADATATOOL |
Manage Twenty MCP metadata schema operations. |
twenty_mcp_oauth |
OAUTHTOOL |
Manage Twenty MCP OAuth and Webhooks operations. |
twenty_provision_api_key |
GRAPHQLTOOL |
Programmatically provision a long-lived Twenty API key from user credentials (login->token->createApiKey->generateApiKeyToken on /metadata). Day-0 provisioning primitive. |
Verbose 1:1 API-mapped tools (MCP_TOOL_MODE=verbose or both)
49 per-operation tools — one per public API method (click to expand)
| MCP Tool | Toggle Env Var | Description |
|---|---|---|
twenty_batch_create_records |
CRM_APITOOL |
Batch create up to 60 records for any object. |
twenty_batch_delete_records |
CRM_APITOOL |
Batch delete up to 60 records by ID for any object. |
twenty_batch_update_records |
CRM_APITOOL |
Batch update up to 60 records for any object. |
twenty_client_credentials_oauth_token |
OAUTH_APITOOL |
Perform a server-to-server client credentials flow to get a workspace-scoped token. |
twenty_create_company |
CRM_APITOOL |
Create a company in CRM. |
twenty_create_metadata_field |
METADATA_APITOOL |
Create a custom field on a standard or custom object. |
twenty_create_metadata_object |
METADATA_APITOOL |
Create a new custom object schema (e.g. Invoice). |
twenty_create_metadata_relation |
METADATA_APITOOL |
Create a bidirectional relation between objects. |
twenty_create_opportunity |
CRM_APITOOL |
Create opportunity. |
twenty_create_person |
CRM_APITOOL |
Create a person in CRM. |
twenty_create_record |
CRM_APITOOL |
Create a new record for any custom or built-in object. |
twenty_delete_company |
CRM_APITOOL |
Delete a company by ID. |
twenty_delete_metadata_field |
METADATA_APITOOL |
Delete a custom field from an object schema. |
twenty_delete_metadata_object |
METADATA_APITOOL |
Delete a custom object schema. |
twenty_delete_metadata_relation |
METADATA_APITOOL |
Delete an existing relation by relation ID. |
twenty_delete_opportunity |
CRM_APITOOL |
Delete an opportunity by ID. |
twenty_delete_person |
CRM_APITOOL |
Delete a contact by ID. |
twenty_delete_record |
CRM_APITOOL |
Delete a record by ID for any custom or built-in object. |
twenty_exchange_oauth_token |
OAUTH_APITOOL |
Exchange an authorization code for access and refresh tokens. |
twenty_execute_gql |
CRM_APITOOL |
Execute arbitrary GraphQL queries on core and custom schemas. |
twenty_find_duplicates |
CRM_APITOOL |
Find duplicate records for an object by data payload or record IDs. |
twenty_find_records |
CRM_APITOOL |
Ergonomic record search wrapper mapping to Twenty REST query params. |
twenty_get_companies |
CRM_APITOOL |
Get CRM companies. |
twenty_get_company |
CRM_APITOOL |
Get a specific company by ID. |
twenty_get_metadata |
METADATA_APITOOL |
Fetch complete workspace metadata schema. |
twenty_get_metadata_field |
METADATA_APITOOL |
Fetch a specific field schema by ID. |
twenty_get_metadata_fields |
METADATA_APITOOL |
Fetch all field schemas. |
twenty_get_metadata_object |
METADATA_APITOOL |
Fetch a specific object schema by name or ID. |
twenty_get_metadata_objects |
METADATA_APITOOL |
Fetch all object schemas. |
twenty_get_metadata_relation |
METADATA_APITOOL |
Fetch a specific relation schema by ID. |
twenty_get_metadata_relations |
METADATA_APITOOL |
Fetch all relation schemas. |
twenty_get_oauth_discovery |
OAUTH_APITOOL |
Fetch the standard OAuth configuration server discovery metadata. |
twenty_get_opportunities |
CRM_APITOOL |
Get opportunities. |
twenty_get_opportunity |
CRM_APITOOL |
Get a specific opportunity by ID. |
twenty_get_people |
CRM_APITOOL |
Get CRM contacts. |
twenty_get_person |
CRM_APITOOL |
Get a specific contact by ID. |
twenty_get_record |
CRM_APITOOL |
Fetch a specific record by ID for any custom or built-in object. |
twenty_get_records |
CRM_APITOOL |
Fetch a list of records for any custom or built-in object. |
twenty_refresh_oauth_token |
OAUTH_APITOOL |
Refresh an expired access token using a refresh token. |
twenty_register_oauth_client |
OAUTH_APITOOL |
Register a new OAuth client dynamically per RFC 7591. |
twenty_request_metadata |
METADATA_APITOOL |
Internal helper for Routing Metadata requests under /rest/metadata or /metadata. |
twenty_update_company |
CRM_APITOOL |
Update a company's fields by ID. |
twenty_update_metadata_field |
METADATA_APITOOL |
Update an existing field's metadata configuration. |
twenty_update_metadata_object |
METADATA_APITOOL |
Update a custom object schema. |
twenty_update_metadata_relation |
METADATA_APITOOL |
Update an existing relation by relation ID. |
twenty_update_opportunity |
CRM_APITOOL |
Update an opportunity's fields by ID. |
twenty_update_person |
CRM_APITOOL |
Update a contact's fields. |
twenty_update_record |
CRM_APITOOL |
Update an existing record by ID for any custom or built-in object. |
twenty_validate_webhook_signature |
OAUTH_APITOOL |
Validate an incoming webhook signature using HMAC SHA256 (timing safe). |
6 action-routed tool(s) (default) · 49 verbose 1:1 tool(s). Each is enabled unless its <DOMAIN>TOOL toggle is set false; MCP_TOOL_MODE selects the surface (condensed default · verbose 1:1 · both). Auto-generated — do not edit.
See docs/overview.md or docs/concepts.md for deeper operational examples.
Architecture
This package uses the standardized Agent-Utilities dynamic facade architecture:
graph TD
User([User Agent]) --> Server[FastMCP Server]
Server --> Facade[Api Dynamic Facade]
Facade --> ClientBase[ApiClientBase]
Facade --> Auth[Credentials Auth Handler]
ClientBase --> Service([External Service API])
Deployment
Bare-Metal (Standard pip)
- Set up the operator's Python virtual environment (>= 3.10).
- Install the package:
pip install .[all] - Export credentials:
export TWENTY_URL="http://localhost:3000"
- Run:
python -m twenty_mcp.mcp_server
Container (Docker Compose)
A standard compose structure is provided inside the docker/ folder. Build and deploy:
docker compose -f docker/compose.yml up --build -d
Additional Deployment Options
twenty-mcp can run as a local stdio process or container, or behind a remote
network boundary. The
Deployment guide carries
the detailed transport contract.
- Local container — launch a reviewed immutable image as a least-privilege stdio child with no listener or published port.
- Remote URL — connect through an operator-supplied authenticated HTTPS
ingress. Keep its URL, outbound identity references, trust profile, and exact
MCP_ALLOWED_HOSTSinAgentConfig.
Documentation
The complete documentation is published as the official documentation site and is the recommended reference for installation, deployment, and day-to-day operation.
| Page | Contents |
|---|---|
| Installation | pip, source, extras, prebuilt Docker image |
| Deployment | run the MCP and agent servers, Compose, Caddy + Technitium, env config |
| Usage | the MCP tools, the Api client, the A2A agent |
| Backing Platform | deploy Twenty CRM with Docker |
| Overview | the dynamic facade architecture |
| Concepts | concept registry (CONCEPT:TWENTY-*) |
Contributing
Please audit all code changes against the repository's contribution and review requirements, and run:
pre-commit run --all-files
License
This project is licensed under the MIT License. See the LICENSE file for complete details.
Environment Variables
Package environment variables
| Variable | Example | Description |
|---|---|---|
TWENTY_URL |
http://localhost:3000 |
Twenty CRM Base Server URL |
TWENTY_TOKEN |
secret-injected | Developer authentication token |
TWENTY_MCP_BASE_URL |
http://localhost:3000/api |
Base API URL to query |
TWENTY_MCP_USERNAME |
admin |
Auth username for service |
TWENTY_MCP_PASSWORD |
secret-injected | Auth password for service |
TWENTY_TLS_PROFILE |
— | SSL verification flag |
TWENTY_TLS_PROFILE_REF |
— | |
CRMTOOL |
True |
CRM Tool Enabled Flag |
METADATATOOL |
True |
Metadata Tool Enabled Flag |
OAUTHTOOL |
True |
OAuth Tool Enabled Flag |
GRAPHQLTOOL |
True |
GraphQL Tool Enabled Flag |
TWENTY_API_PREFIX |
http://localhost:3000/api/v1 |
Twenty API custom path prefix (if needed) |
Inherited agent-connector-sdk variables (apply to every connector)
| Variable | Example | Description |
|---|---|---|
TRANSPORT |
stdio |
MCP transport: stdio | streamable-http | sse |
HOST |
127.0.0.1 |
Loopback bind host (set an authenticated ingress explicitly) |
PORT |
8000 |
Bind port (HTTP transports) |
MCP_TOOL_MODE |
intent |
Tool surface: intent | condensed | verbose | both |
MCP_ENABLED_TOOLS |
— | Comma-separated tool allow-list |
MCP_DISABLED_TOOLS |
— | Comma-separated tool deny-list |
MCP_ENABLED_TAGS |
— | Comma-separated tag allow-list |
MCP_DISABLED_TAGS |
— | Comma-separated tag deny-list |
EUNOMIA_TYPE |
none |
Authorization mode: none | embedded | remote |
EUNOMIA_POLICY_FILE |
mcp_policies.json |
Embedded Eunomia policy file |
EUNOMIA_REMOTE_URL |
— | Remote Eunomia authorization server URL |
ENABLE_OTEL |
False |
Enable OpenTelemetry export |
OTEL_EXPORTER_OTLP_ENDPOINT |
— | OTLP collector endpoint |
MCP_CLIENT_AUTH |
— | Outbound MCP child auth: oidc-client-credentials | basic | none |
OIDC_CLIENT_ID |
— | OIDC client id (service-account auth) |
OIDC_CLIENT_SECRET_REF |
secret://identity/oidc-client-secret |
Runtime secret reference for the OIDC service account |
MCP_BASIC_AUTH_USERNAME |
— | HTTP Basic username (MCP_CLIENT_AUTH=basic) |
MCP_BASIC_AUTH_PASSWORD_REF |
secret://identity/mcp-basic-password |
Runtime secret reference for HTTP Basic auth (MCP_CLIENT_AUTH=basic) |
DEBUG |
False |
Verbose logging |
PYTHONUNBUFFERED |
1 |
Unbuffered stdout (recommended in containers) |
MCP_URL |
http://localhost:8000/mcp |
URL of the MCP server the agent connects to |
PROVIDER |
openai |
LLM provider for the agent |
MODEL_ID |
gpt-4o |
Model id for the agent |
ENABLE_WEB_UI |
True |
Serve the AG-UI web interface |
12 package + 24 inherited variable(s). Auto-generated from .env.example + the shared agent-connector-sdk set — do not edit.
Governed capability contract
This package ships a compact canonical skill surface with specialist procedures
kept as referenced workflows. The current MCP tools, skill metadata,
connector_manifest.yml, ontology, mappings, shapes, fixtures, migrations,
tool-schema fingerprints, and certification metadata form one versioned
capability contract. Validate them together; do not rely on stale tool names or
historical per-task skill wrappers.
Runtime endpoints, credentials, certificate trust, tenant identity, retention, and observability policy are deployment inputs and are never packaged values. See Configuration, trust, and privacy before enabling a network transport, connector ingestion, Arbora delegation, or trace export.
Metadata
Release files for twenty-mcp 2.2.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| twenty_mcp-2.2.0-py3-none-any.whl | Python 3 | none | any | Details |
Release files / twenty_mcp-2.2.0-py3-none-any.whl
| Download URL | twenty_mcp-2.2.0-py3-none-any.whl |
|---|---|
| Size | 76.5 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
2e50470da8e8cb2346651e623ab6ed410c92fd5a7a297cca9bfa26b33dd4dc76
|
|
BLAKE2b-256 checksum How to use checksums |
7edd2f72e97a8787bde168625234b569e6d3e98c02b1498b9a18aa51619d7a0f
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.14.4
|
Security for twenty-mcp 2.2.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.