Borrowing it
Nothing to install: this file belongs to parnexcodes/synthetic-web-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/parnexcodes/synthetic-web-search-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/parnexcodes/synthetic-web-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/parnexcodes/synthetic-web-search-mcp/claude-md)<a href="https://agentmods.dev/instructions/parnexcodes/synthetic-web-search-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/parnexcodes/synthetic-web-search-mcp/claude-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/parnexcodes/synthetic-web-search-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/parnexcodes/synthetic-web-search-mcp/claude-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 | $0.00404 | $0.00404 |
| Opus 5.5 | $0.00162 | $0.00162 |
| Sonnet 5.5 | $0.00081 | $0.00081 |
| Haiku 4.5 | $0.00040 | $0.00040 |
Grade A, and why
synthetic-web-search-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 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.
What it actually says
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
This is a Model Context Protocol (MCP) server that exposes Synthetic's web search API as an MCP tool. It provides a single search_web tool for performing web searches.
Development Commands
# Build the project
npm run build
# Development mode (run with ts-node)
npm run dev
# Watch for changes and auto-rebuild
npm run watch
# Run the compiled server
npm start
# Test with MCP Inspector
npx @modelcontextprotocol/inspector synthetic-web-search-mcp
Architecture
The server is implemented as a single-file MCP server (src/index.ts) with:
- Transport: StdioServerTransport for CLI/Claude Desktop integration
- Single Tool:
search_webwith one required argument (query) - API Endpoint:
https://api.synthetic.new/v2/search
The code flow:
- Server initializes and validates
SYNTHETIC_API_KEYenvironment variable - Server advertises the
search_webtool viaListToolsRequestSchema - Clients call the tool via
CallToolRequestSchema - Server makes POST request to Synthetic API with Bearer token auth
- Results returned as formatted JSON
Testing
No automated tests exist. Test manually using MCP Inspector:
npx @modelcontextprotocol/inspector synthetic-web-search-mcp
The MCP Inspector runs the server via stdio and provides a UI to invoke tools.
Notes
- This is an ES Module project (package.json has
"type": "module") - TypeScript strict mode is enabled (in tsconfig.json)
- No linting or formatting tools are configured
- The server exits with code 1 if
SYNTHETIC_API_KEYis not set
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 · 59 lines · 404 tokens per session scan A 7d0dc19b2e60
synthetic-web-search-mcp CLAUDE.md is an instructions file published in the GitHub repository parnexcodes/synthetic-web-search-mcp (22 stars, last pushed 7mo ago), licensed MIT. It adds 404 tokens to every session, about $0.0016 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 2026-08-30.
synthetic-web-search-mcp CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| synthetic-web-search-mcp CLAUDE.mdparnexcodes/synthetic-web-search-mcp | Instructions file | 22 | 7mo ago | MIT | A | 404 | Claude Code |
| 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 |