AgentOps MCP Server
AgentOps MCP server: the agent reads traces and spans of agent runs to find where they failed
- 14 ★ on the repository
- Last commit
Extended access
Why this level
- Calls the AgentOps API with a project key
- Traces may contain prompts and responses with user data
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add mcp/agentops-mcp-serverDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Calls the AgentOps API with a project key
- Traces may contain prompts and responses with user data
This is third-party code. Review the repository files before installing.
What it does
The server gives the agent access to AgentOps observability data. The auth tool exchanges a project key for a token, get_trace and get_span return a single trace or span, and get_complete_trace returns a full trace with all spans and metrics. This lets the agent inspect a failed run of another agent and explain which step broke.
Who it is for. For agent developers who already send telemetry to AgentOps.
Good fit when
- You need to inspect the trace of a failed agent run
- You need to compare span metrics within one trace
Not a fit when
- Agent telemetry is not collected in AgentOps
- You need to search traces by criteria; the server works only with known IDs
Example request
Open trace 7f3a... in AgentOps and tell me at which step the agent failedMCP
- Transport
- stdio
- Authentication
- API key
Environment variables
AGENTOPS_API_KEYrequired, secret- AgentOps project API key
Limitations
Requires an AgentOps account, a project key and Node.js 18+. There are only four read-only tools and you need the trace ID. The repository has not changed in over a year.
How to disable. Remove the agentops-mcp block from the client's MCP config.
FAQ
Does the server change data in AgentOps?
No, all tools only read traces and spans.
Discussion
No questions or reviews yet.
Related
MCP serversUseAgent’s MCP server sends tasks to remote agents, collects their results and records the runs in an organization’s ledger.
An MCP server that inserts a human feedback step into agent tasks: a web or desktop window for text, images and prompts
An MCP server and CLI coordinate specialized agents, retain working patterns and connect tasks with project hooks.
An MCP server that turns a request into a step plan with dependencies and keeps context across agent sessions
MCP Agent Mail
mcp_agent_mail
A mail coordination layer for coding agents: agents have memorable names, inboxes and outboxes, history search and voluntary file reservations
A bridge between local CLI agents: Codex, Cursor or Claude Code delegate work to Antigravity, Grok, Kimi and seven more.
README in short
The README shows an MCP config running via npx with AGENTOPS_API_KEY, a Cursor deeplink and Smithery install for Claude Desktop. It documents four tools with parameters: auth, get trace, get span and get complete trace. Local build steps are included.