Borrowing it
Nothing to install: this file belongs to agentwebprotocol/mcp-server. 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/agentwebprotocol/mcp-server/main/CLAUDE.mdgit clone --depth 1 https://github.com/agentwebprotocol/mcp-serverWrote 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/agentwebprotocol/mcp-server/claude-md)<a href="https://agentmods.dev/instructions/agentwebprotocol/mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/agentwebprotocol/mcp-server/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/agentwebprotocol/mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/agentwebprotocol/mcp-server/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 | $0.00402 | $0.00402 |
| Opus 5.5 | $0.00161 | $0.00161 |
| Sonnet 5.5 | $0.00080 | $0.00080 |
| Haiku 4.5 | $0.00040 | $0.00040 |
Grade A, and why
mcp-server 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
AWP MCP Server
MCP server that gives Claude Code (and any MCP-compatible AI tool) native access to the AWP specification, validator, and generator. Published on npm as awp-mcp-server.
Ecosystem
| Repo | Role |
|---|---|
| spec | Source of truth — the specification |
| agentwebprotocol.org | Standards website |
| agent-json.org | Schema reference and validator site |
| agent.json | npm CLI (npx agent-json init) |
| mcp-server (this repo) | MCP server for Claude Code |
GitHub org: github.com/agentwebprotocol
Installation (for users)
Add to ~/.claude/mcp.json:
{
"mcpServers": {
"awp": {
"command": "npx",
"args": ["awp-mcp-server"]
}
}
}
Tools Provided
| Tool | Description |
|---|---|
awp_get_spec |
Returns the full AWP specification |
awp_validate |
Validates agent.json content |
awp_generate |
Generates agent.json from parameters |
awp_examples |
Returns 3 example agent.json files |
awp_quickstart |
Step-by-step implementation guide |
Key Files
src/index.js— MCP server with embedded spec and all 5 tools
Design Decisions
- Spec is embedded in the source (works offline, no network dependency)
- Single file server — keeps it simple
Publishing
npm version patch # bump version
npm publish # publish to npm
npm account: bshyong158. Auth token in 1Password (Clawdbot vault, "Npmjs" item).
When Spec Changes
Update the embedded spec string in src/index.js, bump version, and publish.
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 · 63 lines · 402 tokens per session scan A e4c6e2711ca8
mcp-server CLAUDE.md is an instructions file published in the GitHub repository agentwebprotocol/mcp-server (0 stars, last pushed 7mo ago), licensed MIT. It adds 402 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 2026-08-31.
mcp-server CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mcp-server CLAUDE.mdagentwebprotocol/mcp-server | Instructions file | 0 | 7mo ago | MIT | A | 402 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |