agentmods.dev

mcp-httpserver-proxy CLAUDE.md

Project instructions for mcp-httpserver-proxy, a bridge that connects Model Context Protocol clients to HTTP servers. They explain its transport design, commands, and coding rules.

In plain words
What is it for?
Use them when developing, testing, formatting, or reviewing this TypeScript proxy and its standard-input/output and server-sent-events connections.
Why use it?
They prevent ordinary log messages from corrupting the JSON messages that clients use to communicate, and provide consistent build, test, formatting, and review guidance.

Instructions file

2 9d ago A scan 515 tokens original MIT
View the source file shailesh17/mcp-httpserver-proxy
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/shailesh17/mcp-httpserver-proxy/claude-md
Clone the repo
git clone --depth 1 https://github.com/shailesh17/mcp-httpserver-proxy
Per session 515 This file is loaded in full into every session.
When invoked 515 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 $0.00515 $0.00515
Opus 5 $0.00258 $0.00258
Sonnet 5 $0.00103 $0.00103
Haiku 4.5 $0.00052 $0.00052

Measured yesterday against content hash 5758a41d4b34, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-httpserver-proxy 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 yesterday.

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.

CLAUDE.md · 41 lines

How it starts

The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Code Guidelines for mcp-httpserver-proxy

Welcome, Claude! This document details the technical architecture, strict constraints, development workflows, and Pull Request procedures for mcp-httpserver-proxy.

⚠️ Critical Constraint: Sacred Standard Output (stdout)

[!IMPORTANT] NEVER use console.log() or write arbitrary text to process.stdout! The client (Claude Desktop, Cursor, etc.) parses stdout strictly as JSON-RPC Model Context Protocol messages. Any non-protocol output on stdout will corrupt the transport and crash the client session.

All logging, informational messages, and diagnostics MUST be routed to process.stderr via console.error().

🛠️ Common Commands

  • Build: pnpm run build (tsc)
  • Test: pnpm test (node --test test/**/*.test.ts)
  • Format: pnpm run format (trunk fmt)
  • Lint & Static Analysis: pnpm run check (trunk check)
  • Dev Watch Mode: pnpm run dev

🏗️ Architecture & Transports

  • Transport Bridge: Transparently connects an MCP Client over stdio (StdioServerTransport) to an MCP HTTP Server over Server-Sent Events (SSEClientTransport).
  • Transport Lifecycle Order: Establish and confirm the SSE backend connection (sseTransport.start()) before starting stdioTransport.start().
  • Custom HTTP Headers: Configured via repeated -H / --header flags and MCP_PROXY_HEADERS environment variable.
  • Resilient Connection Retries: Configured via --retries (-r) and --retry-delay (-d) with exponential backoff.

📝 Coding & Commit Standards

  • Conventional Commits: All commit messages and PR titles must follow <type>(<scope>): <description> (e.g. feat(cli): add header flag, docs(claude): add CLAUDE.md).
  • Pre-flight Checks: Always run pnpm test, pnpm run format, and pnpm run check before submitting.
  • Dependency Management: Use pnpm exclusively. Never introduce npm or yarn lockfiles.

Read the full file on GitHub · 41 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. yesterday First seen · 41 lines · 515 tokens per session scan A 5758a41d4b34

Subscribe to this mod's changes

mcp-httpserver-proxy CLAUDE.md is an instructions file published in the GitHub repository shailesh17/mcp-httpserver-proxy (2 stars, last pushed 9d ago), licensed MIT. It adds 515 tokens to every session, about $0.0026 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 2026-08-31.

Data and AIGit and workflowTestingaerospikeai-agentsclaude-desktopcursordeveloper-toolsmcp
Related

Other instructions, from other repositories

mcpm.sh CLAUDE.md

Instructions for pathintegral-institute/mcpm.sh: This file contains conventions that Claude should follow when working on this project.

pathintegral-institute/mcpm.sh · 202 tokens

mcpm.sh GEMINI.md

Instructions for pathintegral-institute/mcpm.sh: Reference CLAUDE.md for project conventions.

pathintegral-institute/mcpm.sh · 11 tokens

Basecamp-MCP-Server CLAUDE.md

Instructions for georgeantonopoulos/Basecamp-MCP-Server, covering claude.md, development commands, setup (one-time) - requires python 3.10+, option 2: using pip (if python 3.10+ already installed) and oauth authentication.

georgeantonopoulos/Basecamp-MCP-Server · 1,662 tokens

ls-mcp AGENTS.md

Instructions for lirantal/ls-mcp, covering agents.md, start here, documentation, prs and issues and releases.

lirantal/ls-mcp · 357 tokens

brightspace-mcp-server AGENTS.md

Instructions for RohanMuppa/brightspace-mcp-server, covering project rules, when adding a new feature, commit format, npm publishing and architecture.

RohanMuppa/brightspace-mcp-server · 354 tokens

cosmos-mcp CLAUDE.md

Instructions for teampolarity/cosmos-mcp, covering cosmos-mcp, layout, tools (authoritative list in src/tools/index.ts), cli subcommands and imessage is the headline source.

teampolarity/cosmos-mcp · 1,310 tokens