What is synthetic-search-mcp AGENTS.md?

A set of project instructions for an MCP server that exposes search tools through JSON-RPC over standard input and output, using the hosted Synthetic API.

Use it when building, testing, or running the Synthetic search MCP server.

It documents setup, supported checks, testing, and the fact that the server must be used through an MCP client rather than a web request.

How baanish/synthetic-search-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to baanish/synthetic-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.

Copy the file

curl -O https://raw.githubusercontent.com/baanish/synthetic-search-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/baanish/synthetic-search-mcp

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/baanish/synthetic-search-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/baanish/synthetic-search-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/baanish/synthetic-search-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/baanish/synthetic-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/baanish/synthetic-search-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/baanish/synthetic-search-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 613 This file is loaded in full into every session.

When invoked 613 The same file — it is already loaded in full.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00613	$0.00613
Opus 5.5	$0.00245	$0.00245
Sonnet 5.5	$0.00123	$0.00123
Haiku 4.5	$0.00061	$0.00061

Measured 2mo ago against content hash bc4d3fc5181c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

synthetic-search-mcp AGENTS.md scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- The server speaks JSON-RPC over stdio — you cannot `curl` it. Drive it with an MCP client.

AGENTS.md · 36 lines

How it starts

The opening of the file, as written. The whole thing — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Cursor Cloud specific instructions

This repo is @baanish/synthetic-search-mcp, a Node.js (ESM, >=20) TypeScript MCP server that exposes two tools (search and search_quota) over stdio, backed by the hosted Synthetic API (https://api.synthetic.new). There is no HTTP port, database, or frontend.

Standard commands live in package.json (build, dev, start) and README.md. Notes that are not obvious from those files:

npm install automatically runs the prepare script (npm run build → tsc), producing dist/. The update script already runs install on startup.
Gates: npm run typecheck (tsc --noEmit, strict) and npm test (Vitest — unit, fetch-mocked integration, MCP transport tests covering both the 2025 era (in-memory pair) and the stateless 2026-07-28 revision plus legacy compatibility (in-process createMcpHandler), a spawned-bin serveStdio entry test (requires dist/, which pretest builds before every npm test, as do prepare and CI), and seeded fuzz tests). npm run build emits dist/. No linter is configured. CI runs typecheck + build + test on Node 20/22.
npm test includes an opt-in live test that calls the real Synthetic API; it is skipped automatically unless SYNTHETIC_API_KEY is set (so CI runs unit/fuzz only).
The server speaks JSON-RPC over stdio — you cannot curl it. Drive it with an MCP client. The @modelcontextprotocol/client Client + StdioClientTransport (a dev dependency) works: spawn node dist/index.js, connect() (with versionNegotiation: { mode: 'auto' } it probes server/discover and falls back to the 2025 initialize handshake), then tools/list → tools/call (search or search_quota).
Runtime MCP dependency is the v2 SDK package @modelcontextprotocol/server (serveStdio serves both protocol eras; see README "Protocol support" for the era/pinning model).
search and search_quota call the real Synthetic API and require SYNTHETIC_API_KEY. In Cursor Cloud this is provided as a secret and injected into the environment. The server still starts without the key (it logs a warning to stderr) but tool calls return an error until the key is set.
Run locally with npm run dev or node dist/index.js (it then waits for stdio MCP traffic).

Read the full file on GitHub · 36 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.

2mo ago Changed · +8 lines · +152 tokens per session bc4d3fc5181c
2mo ago First seen · 28 lines · 461 tokens per session scan A f20d11c42012

Subscribe to this mod's changes

synthetic-search-mcp AGENTS.md is an instructions file published in the GitHub repository baanish/synthetic-search-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 613 tokens to every session, about $0.0025 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

synthetic-search-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
synthetic-search-mcp AGENTS.mdbaanish/synthetic-search-mcp	Instructions file	0	1mo ago	MIT	A	613	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

synthetic-search-mcp: Instructions file for Codex