MCP

MCP is powered by insight search, so your agent can query your production data with natural language and use that context to find root causes, fix issues, and optimize your agent.

Prerequisites#

• A Context Company account with at least one project sending data
• An MCP-compatible IDE or tool (Cursor, Claude Code, Windsurf, or any client that supports MCP)

Setup#

One-click install via OAuth — no API key needed. For CI, programmatic, or headless setups, see Advanced: API key below.

Claude Code:

claude mcp add --transport http context-company https://api.thecontext.company/mcp

Then run claude, type /mcp, select context-company, and press Enter to complete the OAuth sign-in.

Cursor / other MCP clients:

{
  "mcpServers": {
    "context-company": {
      "url": "https://api.thecontext.company/mcp"
    }
  }
}

Sign in through your client's MCP connection UI to complete the OAuth flow.

Try it out:

Use The Context Company MCP to show me my last 5 production agent runs, including their status and cost.

Advanced: API key#

For CI, programmatic, or headless setups where OAuth isn't practical, authenticate with a read-only API key instead.

Cursor may ignore Authorization headers when the MCP server advertises OAuth discovery — the OAuth flow above is recommended for Cursor. API keys still work for Claude Code, CI, and other programmatic or headless MCP clients.

Generate a read-only API key from the Access Data page in your dashboard (prefixed tcc_key, cannot ingest traces), choosing a Dev only / Prod only / Dev + Prod scope. Then:

claude mcp add --transport http context-company \
  https://api.thecontext.company/mcp \
  --header "Authorization: Bearer <your-api-key>"

Available tools#

For most questions, insight_search is the right choice — a multi-step analytics agent with full SQL access to your telemetry that synthesizes evidence across runs, sessions, patterns, failures, and costs. The other tools fetch raw traces and lists, best used when you already have a specific ID or want a filtered list.

insight_search#

Ask natural-language questions about your production data including metrics, patterns, failures, sessions, costs, and more.

Insight search queries production data only and requires a Pro or Enterprise plan.

get_agent_runs#

Fetch a filtered raw list of runs for dev or prod. summary (default) returns compact runs with prompt/response previews; full_trace includes all steps and tool calls.

get_agent_sessions#

Fetch a filtered list of sessions — same filters as get_agent_runs, matches when any run in the session qualifies.

get_agent_run#

Fetch the full raw trace of a single run by ID, including all steps and tool calls.

get_agent_session#

Fetch a specific production session by session ID. return_type: conversation (default, prompt/response only) or full_trace.

Example prompts#

Frustration debugging

Find the biggest reason users have been frustrated in my runs this past week. Look at my codebase to find the root cause and fix it.

Tool failure chains

Find runs where a tool call failed right after another tool succeeded. What's the most common pattern, and what in my code is causing it?

Cost optimization

Find my most expensive runs from the past week. Figure out which prompts or tool loops are driving up cost and suggest code changes to reduce token usage.

Redundant tool loops

Find runs where my agent called the same tool more than 3 times in a row. Is there a loop in my code causing redundant calls? Fix it.

Task failure improvement

Show me runs with task failure patterns. Compare what the user asked for vs what the agent did, and suggest how to improve my system prompt.