signals-scout-mcp-tool-calls — Claude Code skill: what it does
signals-scout-mcp-tool-calls — a PostHog Signals skill that sifts $mcp_tool_call telemetry for MCP tools agents struggle with, then files one report per product category.
no license 194 installs ★ 101 updated 2026-11-16
npx skills add PostHog/ai-plugin --skill signals-scout-mcp-tool-calls -a claude-codeWhat signals-scout-mcp-tool-calls does
Inside the PostHog Signals agent (Claude sandbox), this skill queries the $mcp_tool_call event and looks for MCP tools agents cannot use cleanly. Error share counts only when volume and reach back it up, so failures get weighed against distinct users and sessions. Retry loops inside one session, slow p95 $mcp_duration_ms, oversized responses and a jump in call frequency against the previous window are findings too. Tools are bucketed by $mcp_tool_category, the product team that owns them.
Field coverage comes first. A precheck query over the last 7 days tells whether the event arrives at all, then the skill checks which properties the project actually sends: PostHog's own hono server carries $mcp_error_type and the category, external SDK servers carry the raw error text. Two reference files, references/queries.md and references/metrics-dashboard.md, hold the SQL and the dashboard recipe and are opened as needed. Every problem tool leaves with a fix hypothesis attached, written through emit_report; a category that already has a live report gets amended with edit_report rather than a second one.
Access is the gate: execute-sql, read-data-schema, write on the scratchpad and on the report channel. Without the Signals agent in the Claude sandbox nothing runs. A run that turns up nothing is a valid outcome.
What it helps with
- spot MCP tools failing at a high rate on real traffic
- separate a genuine break from single-user noise
- explain why agents keep calling the same tool in a loop
- file a per-category report with a concrete fix
- catch a tool whose call volume jumped
Example prompts for the agent
- Run the scout over our MCP tool calls and list the tools that fail most.
- Check
$mcp_tool_callfor the past week and file a report for the category with problem tools. - Update the report for that category, a new tool joined the broken ones.
How to install signals-scout-mcp-tool-calls
1Skills CLI (Vercel)
npx skills add PostHog/ai-plugin --skill signals-scout-mcp-tool-calls -a claude-code2Manually: put the files in place
~/.claude/skills/signals-scout-mcp-tool-calls/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/signals-scout-mcp-tool-calls/
1Skills CLI (Vercel)
npx skills add PostHog/ai-plugin --skill signals-scout-mcp-tool-calls -a codex2Manually: put the files in place
.agents/skills/signals-scout-mcp-tool-calls/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add PostHog/ai-plugin --skill signals-scout-mcp-tool-calls -a cursor2Manually: put the files in place
.cursor/skills/signals-scout-mcp-tool-calls/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install PostHog/ai-plugin skills/signals-scout-mcp-tool-calls2Manually: put the files in place
.github/skills/signals-scout-mcp-tool-calls/SKILL.md1Skills CLI (Vercel)
npx skills add PostHog/ai-plugin --skill signals-scout-mcp-tool-calls -a gemini-cli2Platform CLI
gemini skills install https://github.com/PostHog/ai-plugin --path skills/signals-scout-mcp-tool-callsManually: put the files in place
.devin/skills/signals-scout-mcp-tool-calls/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add PostHog/ai-plugin --skill signals-scout-mcp-tool-calls -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about signals-scout-mcp-tool-calls
How do I install signals-scout-mcp-tool-calls in Claude Code?
Run npx skills add PostHog/ai-plugin --skill signals-scout-mcp-tool-calls -a claude-code. The skill file then sits at ~/.claude/skills/signals-scout-mcp-tool-calls/SKILL.md.
What does signals-scout-mcp-tool-calls do?
It reads $mcp_tool_call telemetry, finds MCP tools that get in the way of agents, and groups them by product category. Each category with problem tools gets one report carrying a suggested fix.
What access does the skill need?
The PostHog Signals agent in a Claude sandbox, plus analytics access: execute-sql, read-data-schema, and write on the scratchpad and the report channel. Reports go out through emit_report, edits through edit_report.