agentmods.dev

mcp CLAUDE.md

Repository instructions for a PostHog MCP server, a bridge that lets AI clients such as Claude Desktop, Cursor, and Windsurf access PostHog analytics data. They describe the TypeScript codebase, its Cloudflare Workers runtime, and development commands.

In plain words
What is it for?
Use them to develop, format, lint, deploy, generate types, build schemas, and navigate the TypeScript and planned Python implementations.
Why use it?
They help an agent understand the project layout and use the intended commands when changing or checking the server.

Instructions file

151 7mo ago A scan 1,247 tokens original MIT archived
View the source file PostHog/mcp
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/posthog/mcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/PostHog/mcp
Per session 1,247 This file is loaded in full into every session.
When invoked 1,247 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.01247 $0.01247
Opus 5 $0.00624 $0.00624
Sonnet 5 $0.00249 $0.00249
Haiku 4.5 $0.00125 $0.00125

Measured 2d ago against content hash 8838a923e29d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

CLAUDE.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Development Commands

  • pnpm run dev - Start development server using Wrangler
  • pnpm run deploy - Deploy to Cloudflare Workers
  • pnpm run format - Format code using Biome
  • pnpm run lint:fix - Lint and fix code using Biome
  • pnpm run schema:build:json - Generate JSON schema from Zod schemas for Python/other language implementations
  • wrangler types - Generate TypeScript types for Cloudflare Workers

Code Architecture

This is a PostHog MCP (Model Context Protocol) server built on Cloudflare Workers that provides API access to PostHog analytics data. The server acts as a bridge between MCP clients (like Claude Desktop, Cursor, Windsurf) and PostHog's API.

Project Structure

The repository is organized to support multiple language implementations:

mcp/
├── typescript/          # TypeScript implementation
│   ├── src/            # TypeScript source code
│   ├── tests/          # TypeScript tests
│   └── scripts/        # TypeScript build scripts
├── python/             # Python implementation (planned)
├── schema/             # Shared schema files for all implementations
│   └── tool-inputs.json # Generated JSON schema for cross-language compatibility
├── biome.json          # Shared code formatting configuration
└── CLAUDE.md           # Project documentation

Key Components (TypeScript Implementation)

  • Main MCP Class (typescript/src/integrations/mcp/index.ts): MyMCP extends McpAgent and defines all available tools for interacting with PostHog
  • Unified API Client (typescript/src/api/client.ts): ApiClient class provides type-safe methods for all PostHog API interactions with proper error handling and schema validation
  • Schema Validation (typescript/src/schema/): Zod schemas for validating API requests and responses
  • Tool Input Schemas (typescript/src/schema/tool-inputs.ts): Centralized Zod schemas for all MCP tool inputs, exported to schema/tool-inputs.json for other language implementations
  • Caching (typescript/src/lib/utils/cache/): User-scoped memory cache for storing project/org state
  • Documentation Search (typescript/src/inkeepApi.ts): Integration with Inkeep for PostHog docs search
  • Utility Functions (typescript/src/lib/utils/api.ts): Helper functions for pagination and URL generation

Read the full file on GitHub · 102 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 102 lines · 1,247 tokens per session scan A 8838a923e29d

Subscribe to this mod's changes

mcp CLAUDE.md is an instructions file published in the GitHub repository PostHog/mcp (151 stars, last pushed 7mo ago), licensed MIT. It adds 1,247 tokens to every session, about $0.0062 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Analytics and metricsCode reviewDevOps and cloudfeature-flagsllmsmcpmcp-serverposthog
Related

Other instructions, from other repositories

ollama AGENTS.md

AGENTS.md instructions for ollama/ollama, covering agents.md and building.

ollama/ollama · 91 tokens

fastmcp CLAUDE.md

Claude Code instructions for PrefectHQ/fastmcp, covering fastmcp development guidelines, required development workflow, repository structure, core mcp objects and development rules.

PrefectHQ/fastmcp · 4,780 tokens

ollama CLAUDE.md

Claude Code instructions for ollama/ollama: See AGENTS.md for the shared agent instructions for this repository.

ollama/ollama · 21 tokens

llm AGENTS.md

Instructions for simonw/llm, covering agents.md, setting up a development environment and building the documentation.

simonw/llm · 100 tokens

plano CLAUDE.md

Instructions for katanemo/plano, covering claude.md, build & test commands, rust — wasm plugins (must target wasm32-wasip1), rust — brightstaff binary (native target) and rust — tests, format, lint.

katanemo/plano · 1,270 tokens

oumi AGENTS.md

AGENTS.md instructions for oumi-ai/oumi, covering agent instructions, publication policy and working with contributions.

oumi-ai/oumi · 436 tokens