Borrowing it
Nothing to install: this file belongs to nacho4d/mcp-web-search. 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/nacho4d/mcp-web-search/main/AGENTS.mdgit clone --depth 1 https://github.com/nacho4d/mcp-web-searchWrote 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/nacho4d/mcp-web-search/agents-md)<a href="https://agentmods.dev/instructions/nacho4d/mcp-web-search/agents-md"><img src="https://agentmods.dev/badge/instructions/nacho4d/mcp-web-search/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/nacho4d/mcp-web-search/agents-md"><img src="https://agentmods.dev/badge/instructions/nacho4d/mcp-web-search/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 | $0.00472 | $0.00472 |
| Opus 5.5 | $0.00189 | $0.00189 |
| Sonnet 5.5 | $0.00094 | $0.00094 |
| Haiku 4.5 | $0.00047 | $0.00047 |
Grade A, and why
mcp-web-search 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.
What it actually says
AGENTS.md
Environment
- Package manager:
uv— useuv runanduv sync, notpip - Python version: 3.12+ (pinned in
pyproject.tomlviarequires-python) - No required environment variables — the server makes unauthenticated requests only
Commands
| Action | Command |
|---|---|
| Install dependencies | uv sync |
| Start server (stdio) | uv run mcp-web-search |
| Start server (HTTP) | uv run mcp-web-search --transport streamable-http --host 127.0.0.1 --port 8000 |
| Build wheel | uv build |
There is no test suite and no lint step at this time.
Tool contracts
Both tools always return a JSON string (never raise). The success field signals outcome.
search_list
- Returns up to 10 results from DuckDuckGo.
- Can fail with
DDGSException: Ratelimit— this is a transient DuckDuckGo rate-limit, not a code bug.
access_site
- Downloads up to 2 MB of raw bytes before cutting off.
- After HTML stripping, content is further capped at 20 000 characters. If truncated,
"truncated": trueis set and the string ends with[... content truncated ...]. - Non-HTML responses (JSON, plain text, etc.) are returned as-is up to the same character cap.
- The User-Agent is spoofed to a Chrome/Linux string — this is intentional to avoid bot-blocking.
Boundaries
Always
- Keep both tools returning JSON strings; never change them to raise exceptions.
- Verify the server starts cleanly (
uv run mcp-web-search) before finishing any task.
Ask First
- Adding any new dependency to
pyproject.toml - Adding a third tool — the two-tool surface is intentional
- Changing default transport, host, or port values
Never
- Commit secrets, API keys, or
.envfiles - Remove the 2 MB download cap or the 20 000-character text cap without explicit instruction — they exist to protect Claude's context window
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 · 48 lines · 472 tokens per session scan A 3ad1e6ac28ea
mcp-web-search AGENTS.md is an instructions file published in the GitHub repository nacho4d/mcp-web-search (0 stars, last pushed 4mo ago), licensed MIT. It adds 472 tokens to every session, about $0.0019 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.
mcp-web-search AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mcp-web-search AGENTS.mdnacho4d/mcp-web-search | Instructions file | 0 | 4mo ago | MIT | A | 472 | 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 |