Codegen MCP integration for AI agents.

Connect AI agents to Codegen through 6 structured actions, including get agent run, get current user, and list agent runs. Review authentication, inputs, wor…

ACTION CONTRACTS
6
AUTHENTICATION
API key
SOURCE STATUS
Provider-backed

CATALOG SOURCE REVIEWED AUGUST 23, 2026 / ACTION NAMES AND SCHEMAS DERIVED FROM WORKING MACHINES PROVIDER SOURCE

CAPABILITY PROFILE

What the Codegen integration exposes

The Codegen Agent App exposes 6 provider-backed actions for developer tools and ai work. Its current contract lets an authorized agent retrieve a single codegen agent run status and result, retrieve the codegen user associated with the api token, and list codegen agent runs for an organization. These operations are called through Working Machines as typed capabilities rather than through browser navigation or copied UI steps.

A connection uses API key. Before execution, the agent can inspect the selected action, its required fields, declared scopes, and expected output contract. Provider credentials remain inside the Working Machines runtime; the calling agent receives the capability and its structured result, not the underlying secret.

For reliable operation, start with the narrowest action that satisfies the task, resolve stable provider identifiers before changing state, and validate the returned object or status after execution. Availability still depends on the connected Codegen account, granted provider permissions, workspace policy, region, plan, and upstream API behavior.

VERIFIED ACTION SAMPLE

Real Codegen capabilities.

Showing 6 of 6 actions. Risk labels are conservative signals based on operation names, not substitutes for provider documentation or runtime policy.

get_agent_runREAD

Retrieve a single Codegen agent run status and result.

INPUTS: org_id / agent_run_id

get_current_userREAD

Retrieve the Codegen user associated with the API token.

list_agent_runsREAD

List Codegen agent runs for an organization.

INPUTS: org_id / user_id / source_type / skip / limit

list_organizationsREAD

List Codegen organizations available to the authenticated API token.

INPUTS: skip / limit

list_repositoriesREAD

List repositories for a Codegen organization.

INPUTS: org_id / skip / limit

list_usersREAD

List users for a Codegen organization.

INPUTS: org_id / skip / limit

INPUT CONTRACTS

Know what the action needs before it runs.

get_agent_run

org_idOPTIONAL
The Codegen organization ID. Omit this field to use the organization ID saved with the credential.
agent_run_idREQUIRED
The Codegen agent run ID to retrieve.

list_agent_runs

org_idOPTIONAL
The Codegen organization ID. Omit this field to use the organization ID saved with the credential.
user_idOPTIONAL
source_typeOPTIONAL
skipOPTIONAL
The number of items to skip before returning results.
limitOPTIONAL
The maximum number of items to return. Codegen allows 1 to 100.

list_organizations

skipOPTIONAL
The number of items to skip before returning results.
limitOPTIONAL
The maximum number of items to return. Codegen allows 1 to 100.

list_repositories

org_idOPTIONAL
The Codegen organization ID. Omit this field to use the organization ID saved with the credential.
skipOPTIONAL
The number of items to skip before returning results.
limitOPTIONAL
The maximum number of items to return. Codegen allows 1 to 100.

PROVIDER-SPECIFIC WORKFLOWS

Jobs this Agent App can support

Inspect Get Agent Run

Retrieve a single Codegen agent run status and result. Use this as a bounded discovery step, retain the returned identifier, and avoid expanding the read beyond the task's stated scope.

get_agent_run

Verify with Get Current User

Retrieve the Codegen user associated with the API token. Compare the returned provider state with the intended outcome and preserve stable IDs or canonical links in the run record.

get_current_user

SAFETY BOUNDARY

Operate Codegen with explicit limits

  • Authorize Codegen with API key and grant only the provider access required by the selected actions.
  • The current action names appear read-oriented, but returned Codegen data may still be sensitive and should be minimized before it enters model context.
  • Do not infer permission from catalog visibility. Workspace policy, connection identity, and upstream authorization still govern execution.
  • No provider scope string is declared on the sampled actions. Verify the connected account's actual permissions in Codegen rather than assuming unrestricted access.
  • After a call, inspect the structured result and execution record before reporting that the Codegen task completed successfully.

CONNECTION MODEL

API key

Codegen API token sent as a Bearer token. Generate it from the Codegen developer settings page: https://codegen.com/token.

Working Machines stores provider credentials behind the execution boundary. An agent can use an authorized connection identity, but catalog discovery alone does not reveal OAuth tokens, API keys, or provider secrets.

READ SIGNALS
6
WRITE SIGNALS
0
HIGH IMPACT
0
REVIEW SIGNALS
0

EVIDENCE AND AVAILABILITY

Provider reference

Action names, input fields, authentication types, and counts on this page are generated from the Working Machines provider catalog. Provider behavior, quotas, object semantics, account eligibility, and regional availability remain governed by Codegen.

Official Codegen website

ONE CONNECTION. REAL WORK.

Give your agent software it can use.

Connect through MCP or explore the Agent App catalog and choose only the capabilities your workflow needs.

EXPLORE AGENT APPS