OpenLinker
Sign in
← Back to directory
MCP · HTTP

MCP 合成运行事件读取

Call through OpenLinker

Client connection

Where does MCP take effect?

Configure MCP services in the client or Agent runtime that will call them. Here you can inspect services, try them and copy connection settings.

The web app does not currently associate or distribute MCP tools to Runtime Agents. Copying settings or trying a service does not install tools for this Agent.

After setup, check the connection and tool list in the client running your Agent. Its permissions and policies still determine which tools are available.

This connection calls only this Agent and limits run results to it.

  1. 1. Prepare a User Token

    Use your own User Token; browser credentials do not authenticate MCP. Calling requires agents:run, reading results requires runs:read, and cancellation requires runs:cancel. Agent run access can be restricted.

    Manage User Tokens

  2. 2. Set a local environment variable

    Set OPENLINKER_USER_TOKEN to your own User Token in the environment used to launch Claude Code. Do not put the token in project configuration or commit it.

  3. 3. Merge the client configuration

    Merge the entry below into mcpServers in your project's .mcp.json, preserving existing services. The client resolves the environment variable.

    Loading…
    Protocol endpoint

    Use this URL in a Streamable HTTP client. This page URL is for browsing only.

    Share this page

  4. 4. Check the connection in your client

    Start Claude Code and use /mcp to inspect the connection and tools. Review the business inputs before calling. Copying configuration does not run a task.

    initialize → tools/list → start_agent_run → get_run. Read results while pending; reuse idempotency_key when retrying the same intent.

Client verification record

Claude Code 2.1.289 · HTTP · 2026-10-05 16:56 UTC. Platform and dedicated connections were tested through a local Hosted Web proxy and synthetic service for initialization, discovery, synchronous/asynchronous calls and result retrieval. This is not a live check of this instance or service. Other clients have no verified template yet.

Call protocol and tools · 6

These are OpenLinker invocation and run management tools. Put business arguments inside input, following the business capability.

This connection pins an Agent. agent_id may be omitted; if supplied, it must match the endpoint UUID. Use the input schema discovered by your client.

After connecting, inspect the discovered tool definitions for full arguments and permissions.

run_agent

Invoke and wait for a result. Runtime Agents may still return pending/running; continue reading the Run in that case.

Required arguments
input, idempotency_key
Required permission
agents:run

start_agent_run

Start a call and return a Run immediately. Use its id to inspect progress.

Required arguments
input, idempotency_key
Required permission
agents:run

get_run

Read an authorized Run's status and result. A dedicated connection also requires the Run to belong to this Agent.

Required arguments
run_id
Required permission
runs:read

list_run_events

Read an event page. Continue with after_sequence and limit.

Required arguments
run_id
Required permission
runs:read

list_run_artifacts

Read run artifacts. The structured result is an object containing items.

Required arguments
run_id
Required permission
runs:read

cancel_run

Request cancellation of an authorized non-terminal Run. The server determines its resulting status.

Required arguments
run_id
Required permission
runs:cancel
JSON-RPC example
{
  "jsonrpc": "2.0",
  "id": 3,
  "method": "tools/call",
  "params": {
    "name": "start_agent_run",
    "arguments": {
      "input": {
        "run_id": "f8d01b44-8111-4d95-80c5-a7f710e93154"
      },
      "idempotency_key": "<new-key-for-this-intent>"
    }
  }
}
Connection troubleshooting

Use the errors reported by your client. This page does not probe it.

Missing token or configuration
Confirm OPENLINKER_USER_TOKEN is available to the client process and .mcp.json has been merged.
401 / 403 or permission error
Check the User Token's expiration, revocation, required permissions and resource scope. Browser credentials cannot authenticate MCP.
404 / resource unavailable
Check the instance, Agent UUID, visibility and token scope. This response does not reveal whether a resource exists or was withdrawn.
Connection failure / timeout / 405
Check the protocol URL, HTTPS and network. Use the HTTP configuration: detail pages are not protocol endpoints, and standalone SSE requests are not supported.
Invalid arguments / execution failed
Follow the tool input schema and inspect the Run status, errors and events. Continue reading asynchronous runs; reuse idempotency_key only to retry the same intent.

Verify a business call first

Review the parameters and explicitly call the service here. Inspect its result before configuring your own MCP client.

Platform trial