Borrowing it
Nothing to install: this file belongs to nanwer/trip-search-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/nanwer/trip-search-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/nanwer/trip-search-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/nanwer/trip-search-mcp/agents-md)<a href="https://agentmods.dev/instructions/nanwer/trip-search-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/nanwer/trip-search-mcp/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/nanwer/trip-search-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/nanwer/trip-search-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.02670 | $0.02670 |
| Opus 5.5 | $0.01068 | $0.01068 |
| Sonnet 5.5 | $0.00534 | $0.00534 |
| Haiku 4.5 | $0.00267 | $0.00267 |
Grade A, and why
trip-search-mcp AGENTS.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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent / Claude Code instructions
Read this first. Re-read it whenever a previous session gave wrong advice — there's a high chance the same mistake is repeating.
Deployment topology (CRITICAL — sessions have gotten this wrong)
There is only one instance of this MCP server. It runs as a local
stdio subprocess that Claude Desktop spawns on Nophil's Mac, configured
in ~/Library/Application Support/Claude/claude_desktop_config.json.
There is NO remote server. There is NO home server. There is NO Cloudflare Tunnel. There is NO HTTP transport. HTTP transport was listed as a future Phase 2-ish item in the original SPEC.md, but it was never built — the project shipped stdio-only and has stayed stdio-only.
claude.ai web sessions CAN call this tool. They reach the local Claude Desktop subprocess through Anthropic's account-level MCP bridge — when you're logged into the same account on both claude.ai and Claude Desktop, the web client can invoke tools registered locally. There is still only one server process, and it lives inside Claude Desktop on the Mac.
How to fix "the tool call timed out / behaves stale" from EITHER client
The fix is the same regardless of whether the failing call came from Claude Desktop, Claude Code, or claude.ai web:
- ⌘Q Claude Desktop (full quit; closing the window doesn't kill the subprocess).
- Reopen Claude Desktop.
- Retry from whichever client you were using.
After the restart, sanity-check the subprocess is running on current code:
ps -o lstart=,command= -p $(pgrep -f trip_search_mcp.server | head -1)
The start time should be recent. If it's older than the latest commit that fixed your issue, the restart didn't take — force-quit Claude through Activity Monitor and reopen.
Past hallucinations to NOT repeat
A prior claude.ai session diagnosed a timeout as "the remote server on your home server reached via Cloudflare Tunnel is on stale code." That diagnosis was invented out of whole cloth — there is no such deployment. Don't suggest:
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.
- 2mo ago First seen · 201 lines · 2,670 tokens per session scan A 76d6b0827872
trip-search-mcp AGENTS.md is an instructions file published in the GitHub repository nanwer/trip-search-mcp (5 stars, last pushed 5mo ago), licensed MIT. It adds 2,670 tokens to every session, about $0.0107 per session on Opus 5.5. 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.
trip-search-mcp AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| trip-search-mcp AGENTS.mdnanwer/trip-search-mcp | Instructions file | 5 | 5mo ago | MIT | A | 2,670 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |