Borrowing it
Nothing to install: this file belongs to webweaver-nexus/webweaver-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/webweaver-nexus/webweaver-mcp-server/main/CLAUDE.mdgit clone --depth 1 https://github.com/webweaver-nexus/webweaver-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/webweaver-nexus/webweaver-mcp-server/claude-md)<a href="https://agentmods.dev/instructions/webweaver-nexus/webweaver-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/webweaver-nexus/webweaver-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/webweaver-nexus/webweaver-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/webweaver-nexus/webweaver-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 | $0.03945 | $0.03945 |
| Opus 5.5 | $0.01578 | $0.01578 |
| Sonnet 5.5 | $0.00789 | $0.00789 |
| Haiku 4.5 | $0.00394 | $0.00394 |
Grade A, and why
webweaver-mcp-server CLAUDE.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 15d 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.
- **No tests.** Verification is via the README's `curl` checks, `npm run check:contract`, MCP Inspector (the default harness), and the vendored `tools/basic-host` harness for model-context updates. How it starts
The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Guidance for Claude Code when working in this repo. For commands, deployment, verification curls, and known limitations, see README.md — this file focuses on the architectural mental model and editing gotchas.
Project Overview
MCP server that exposes WebWeaver Nexus's services to external AI hosts (Claude Desktop, claude.ai custom connectors, ChatGPT, Gemini, etc.) — not consumed by our own landing page or by the Python support agent. Production: https://webweaver-nexus-mcp.vercel.app/mcp.
Three model-facing tools — get_contact_form (MCP App with a natively rendered contact form), get_product_overview, get_contact_info — plus submit_contact_form, which carries _meta.ui.visibility: ["app"] so compliant hosts hide it from the model and let only our own App call it.
For the WebWeaver Nexus product context (this repo's role within Tier 3), see ../CLAUDE.md and ../README.md at the parent folder.
Architecture
Two-process model, communicating across the MCP wire protocol:
- Server (Node + Express + MCP SDK) — registers tools and resources, handles JSON-RPC over Streamable HTTP (or stdio).
- Client App (browser, runs in an iframe inside the MCP host) —
src/mcp-app.ts+mcp-app.html+ CSS, bundled by Vite +vite-plugin-singlefileinto a single self-containeddist/mcp-app.html. Served back to the host as a resource onresources/read.
No shared types between server and client. They communicate over the MCP protocol (JSON-RPC + postMessage via @modelcontextprotocol/ext-apps). Don't try to import across the boundary.
Server: one core, two entry points
server.ts— canonical tool/resource registration. ExportscreateServer(). This is the only place tools are defined.main.ts— local-dev entry. Supports--stdioor HTTP onPORT(default 3001). ImportscreateServer().api/mcp.ts— Vercel serverless entry. Exports the Express app asdefault. ImportscreateServer(). Owns the edge concerns —trust proxy, Host validation, CORS, rate limiting — and mountscreateMcpHandlerviatoNodeHandler.
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.
- 15d ago Changed · +4 lines · +117 tokens per session a52ecbf6d081
- 17d ago Changed · +4 lines · +495 tokens per session 25e30acded93
- 18d ago Changed · +9 lines · +746 tokens per session 78a854ca5cef
- 1mo ago Changed · +8 lines · +938 tokens per session 3596e2bd063d
- 1mo ago First seen · 75 lines · 1,649 tokens per session scan A a96291e1ec5d
webweaver-mcp-server CLAUDE.md is an instructions file published in the GitHub repository webweaver-nexus/webweaver-mcp-server (0 stars, last pushed 2d ago), licensed Apache-2.0. It adds 3,945 tokens to every session, about $0.0158 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.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).