Official PostHog MCP integration for Prime Agent: talks to PostHog's own MCP server (mcp.posthog.com) with a project-scoped personal API key, giving the agent analytics, funnels, path/user-flow analysis, trends, dashboards, and session replay out of the box (MIT).
Drift inferred · capture-to-capture
No drift recorded — single capability capture; advisories appear once its surface changes.
transport — counts 0 tools · 0 res
· 0 prompts
permission surface via code analysis
No tools enumerated yet for this server.
prompt-surface
shipped agent-instruction files + hidden-content / dangerous-code findings —
quoted from the analyzed source
analyzed commit 40d9532 · analyzer v30 · 2w ago
skills & prompt files 1
danger signals2
- suspicious endpoint mcp.posthog.com (telemetry) gbrlpzz-prime-agent-posthog-mcp-40d9532/src/posthog/__init__.py :35
POSTHOG_MCP_URL = "https://mcp.posthog.com/mcp" - suspicious endpoint mcp.posthog.com (telemetry) gbrlpzz-prime-agent-posthog-mcp-40d9532/tests/test_skill.py :101
self.assertEqual(POSTHOG_MCP_URL, "https://mcp.posthog.com/mcp")
evidence-backed
findings quoted directly from the published source artifact — not inferred
code files: 3
filesystem 2
- fs gbrlpzz-prime-agent-posthog-mcp-40d9532/src/posthog/__init__.py :28
from pathlib import Path - fs (weak) gbrlpzz-prime-agent-posthog-mcp-40d9532/tests/test_skill.py :13
from pathlib import Path