Merge Unified's Warp (warp.dev) integration Merge Agent Handler's Warp (warp.dev) MCP server

Connect your AI Agents to Warp (warp.dev) in minutes

Merge lets you securely connect your agents to Warp (warp.dev) and thousands of tools instantly

Start building for free

Read docs

Warp (warp.dev)

Learn more about Merge Agent Handler

Available tools

list_agents

List agent identities for the team. Agent identities are the execution principals a run or schedule can run as. Use getagent for one agent's detail. (For discoverable skills, use listagent_skills instead.)

get_agent

Get full detail for a single agent identity by uid. Use list_agents to find uids.

create_agent

Create a new agent identity. Requires a name. Use listenvironments for environmentid, listmodels for basemodel, listagentskills for skills, and listconnectedselfhostedworkers for worker_host. Returns the new agent uid.

update_agent

Update an agent identity by uid. Only the fields you pass are changed (partial update). Use listagents to find uids; listenvironments/listmodels/listagentskills/listconnectedselfhosted_workers for referenced ids.

delete_agent

Delete an agent identity permanently by uid. The default agent cannot be deleted. Use list_agents to find uids.

get_artifact

Get metadata for a run artifact by uid (type, filename, mime type, size). Artifact uids come from a run's artifacts field (see getrun). Use downloadartifact for the file contents URL.

download_artifact

Get a signed URL to download an artifact's file contents by uid. The API responds with a 302 redirect to a time-limited signed URL. Use get_artifact for metadata only.

list_models

List the LLM models available for agent runs and the team's default model id. Use the returned model ids for basemodel on createagent or config on create_run.

list_environments

List the cloud environments available for agent runs. Use the returned environment uids for environmentid on createagent/update_agent or run config.

list_agent_skills

List discoverable agent skills from the /agent catalog and their variants (skill specs). Use the returned variant ids for skill on createrun or skills on createagent. (For execution-principal agent identities, use list_agents instead.)

list_connected_self_hosted_workers

List self-hosted worker hosts currently connected to the team, with connection counts and heartbeat timestamps. Use the returned workerhost for workerhost on createagent/updateagent.

list_runs

List agent runs with optional server-side filters (state, name, q, creator, modelid, source, executionlocation, scheduleid, date ranges), sorting (sortby/sortorder) and cursor pagination. Use getrun for one run's full detail. Use listmodels/listscheduledagents/listagents to resolve modelid/scheduleid/creator ids.

get_run

Get full detail for a single agent run by id, including state, prompt, creator, timing, and artifacts. Use list_runs to find run ids.

create_run

Start a new agent run from a prompt (or a skill spec). Returns the new runid and initial state. Use listagentskills for skill ids, listagents for agentidentityuid, and listmodels for model ids referenced in config. Poll with getrun.

cancel_run

Cancel an in-flight agent run by id. Only runs whose type is cancellable and that are not already in a terminal state can be cancelled. Use list_runs to find run ids.

get_run_transcript

Get a signed URL to download the full transcript of a run. Use list_runs to find run ids. The API responds with a 302 redirect to a time-limited signed URL.

list_scheduled_agents

List all scheduled agents for the team, including their cron schedule and enabled state. Use getscheduledagent for one schedule's detail.

get_scheduled_agent

Get full detail for a single scheduled agent by id. Use listscheduledagents to find ids.

create_scheduled_agent

Create a scheduled agent that triggers runs on a cron schedule. Requires name and cronschedule. Use listagents for agent_uid. Returns the new schedule id.

update_scheduled_agent

Update a scheduled agent by id. This is a full replace (PUT): name, cronschedule, and enabled are all required. Use listscheduled_agents to find ids.

delete_scheduled_agent

Delete a scheduled agent permanently by id. Use listscheduledagents to find ids.

pause_scheduled_agent

Pause a scheduled agent by id so it stops triggering runs. Use resumescheduledagent to re-enable it. Use listscheduledagents to find ids.

resume_scheduled_agent

Resume a paused scheduled agent by id so it triggers runs again. Use pausescheduledagent to disable it. Use listscheduledagents to find ids.

validate_credential

Validate the configured Warp API key by making a lightweight authenticated request. Returns success true when the key works, false with a reason otherwise.

View all tools by creating a free account See more tools

How to set up Merge Agent Handler

In an mcp.json file, add the configuration below, and restart Cursor.

Learn more in the official documentation ↗

1{
2  "mcpServers": {
3    "agent-handler": {
4      "url": "https://ah-api-develop.merge.dev/api/v1/tool-packs/{TOOL_PACK_ID}/registered-users/{REGISTERED_USER_ID}/mcp",
5      "headers": {
6        "Authorization": "Bearer yMt*****"
7      }
8    }
9  }
10}
11

Copy Code

Open your Claude Desktop configuration file and add the server configuration below. You'll also need to restart the application for the changes to take effect.

Make sure Claude is using the Node v20+.

Learn more in the official documentation ↗

1{
2  "mcpServers": {
3    "agent-handler": {
4      "command": "npx",
5      "args": [
6        "-y",
7        "mcp-remote@latest",
8        "https://ah-api-develop.merge.dev/api/v1/tool-packs/{TOOL_PACK_ID}/registered-users/{REGISTERED_USER_ID}/mcp",
9        "--header",
10        "Authorization: Bearer ${AUTH_TOKEN}"
11      ],
12      "env": {
13        "AUTH_TOKEN": "yMt*****"
14      }
15    }
16  }
17}

Copy Code

Open your Windsurf MCP configuration file and add the server configuration below.
Click on the refresh button in the top right of the Manage MCP server page or in the top right of the chat box in the box icon.

Learn more in the official documentation ↗

1{
2    "mcpServers": {
3      "agent-handler": {
4        "command": "npx",
5        "args": [
6          "-y",
7          "mcp-remote@latest",
8          "https://ah-api.merge.dev/api/v1/tool-packs/<tool-pack-id>/registered-users/<registered-user-id>/mcp",
9          "--header",
10          "Authorization: Bearer ${AUTH_TOKEN}"
11        ],
12        "env": {
13          "AUTH_TOKEN": "<ah-production-access-key>"
14        }
15      }
16    }
17  }

Copy Code

In Command Palette (Cmd+Shift+P on macOS, Ctrl+Shift+P on Windows), run "MCP: Open User Configuration".

You can then add the configuration below and press "start" right under servers. Enter the auth token when prompted.

Learn more in the official documentation ↗

1{
2  "inputs": [
3    {
4      "type": "promptString",
5      "id": "agent-handler-auth",
6      "description": "Agent Handler AUTH_TOKEN", // "yMt*****" when prompt
7      "password": true
8    }
9  ],
10  "servers": {
11    "agent-handler": {
12      "type": "stdio",
13      "command": "npx",
14      "args": [
15        "-y",
16        "mcp-remote@latest",
17        "https://ah-api-develop.merge.dev/api/v1/tool-packs/{TOOL_PACK_ID}/registered-users/{REGISTERED_USER_ID}/mcp",
18        "--header",
19        "Authorization: Bearer ${input:agent-handler-auth}"
20      ]
21    }
22  }
23}