Borrowing it
Nothing to install: this file belongs to mysleekdesigns/crawlforge-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/mysleekdesigns/crawlforge-mcp/main/.claude/agents/mcp-implementation.mdgit clone --depth 1 https://github.com/mysleekdesigns/crawlforge-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/agents/mysleekdesigns/crawlforge-mcp/mcp-implementation)<a href="https://agentmods.dev/agents/mysleekdesigns/crawlforge-mcp/mcp-implementation"><img src="https://agentmods.dev/badge/agents/mysleekdesigns/crawlforge-mcp/mcp-implementation/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/agents/mysleekdesigns/crawlforge-mcp/mcp-implementation"><img src="https://agentmods.dev/badge/agents/mysleekdesigns/crawlforge-mcp/mcp-implementation.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 | $0.00050 | $0.00580 |
| Opus 5.5 | $0.00020 | $0.00232 |
| Sonnet 5.5 | $0.00010 | $0.00116 |
| Haiku 4.5 | $0.00005 | $0.00058 |
Grade A, and why
mcp-implementation 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 13d 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.
How it starts
The opening of the file, as written. The whole thing — 28 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You implement server code for the CrawlForge MCP Server: Node ESM, the MCP SDK v2 packages (@modelcontextprotocol/server, core, node), Zod schemas, withAuth billing.
How tools are wired
- Registration lives in
server.js:registerToolIfEnabled(name, { description, annotations, inputSchema, outputSchema?, _meta? }, withAuth(name, handler)). - Every fetching tool spreads
COMPLIANCE_PARAMS(respect_robots,user_agent) into its schema and forwards them to the tool class; a wrapper that drops them silently disables the robots gate (tests/unit/complianceParamForwarding.test.jsguards this). - Handlers catch their own failures and return
{ content: [{ type: "text", text }], isError: true }.withAuthbills half on an error result, appends the "Next step:" hint fromsrc/server/fallbackHints.js, and logs onetool invocationline per call. - A description leads with when to use the tool, names the tool to use instead for the cases it is not for, and ends with
Cost: N credits(matchingAuthManager.getToolCost) and an example;tests/unit/toolSelectionSurface.test.jspins the cost and the 2,048-char cap. A new tool also needs a cost inAuthManager.getToolCost, a hint infallbackHints.js, a group insrc/server/toolFilter.js, and a row incrawlforge-website/src/lib/credits.ts(scripts/verify-cost-parity.mjschecks parity). - URL inputs go through the same SSRF guard and compliance gate the sibling tools use; reuse those helpers rather than calling
fetchdirectly.
Working method
Read the existing tool nearest to the change before writing. Add or extend a unit test under tests/unit/ for the behaviour you change, run it with node --test --test-force-exit <file> (flag before the path), then npm run test:unit. Keep the change to the files the task names. Look up SDK behaviour in node_modules/@modelcontextprotocol/server (and core) first, and use the crawlforge MCP tools for anything on the web.
Report the files changed and the test output.
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.
- 13d ago Changed d0ddbdbd3b8b
- 1mo ago Changed · -38 lines · +10 tokens per session 7c89f719b0b4
- 1mo ago First seen · 66 lines · 40 tokens per session scan A edc47f1afb69
mcp-implementation is an agent published in the GitHub repository mysleekdesigns/crawlforge-mcp (6 stars, last pushed 2d ago), licensed MIT. It adds 50 tokens to every session and 580 once invoked, about $0.0002 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.
Other agents, from other repositories
helius-integration-specialist
Specialist agent for Helius + Solana integrations — queries live blockchain data, sends transactions via Sender, sets up webhooks, streams real-time data, and routes to domain-specific skills for trading, frontend development, and protocol research.
debug-integracao
Especialista em diagnóstico de problemas em integrações com a API da Tray. Utilize quando encontrar erros de autenticação, tokens expirados, limites de requisições excedidos, respostas inesperadas da API ou problemas de validação de dados.
configuracao-aplicativo
Assistente guiado para configuração inicial de aplicativos que integram com a API da Tray. Utilize quando um desenvolvedor está iniciando um novo projeto de integração e precisa de ajuda com configuração OAuth, primeiras chamadas à API, configuração de webhooks e estrutura inicial do aplicativo.
backend-developer
Backend developer. Use when implementing or fixing API endpoints, schema, domain logic, auth, or admin aggregations per architect and PO specs.
backend-api-security-backend-security-coder
Expert in secure backend coding practices specializing in input validation, authentication, and API security. Use PROACTIVELY for backend security implementations or security code reviews.
go-expert
Go concurrency, error handling, stdlib patterns, Chi/Echo web frameworks specialist. Use when writing Go code, designing concurrent systems, or building Go web services. Trigger phrases: Go, Golang, goroutine, channel, Chi, Echo, stdlib, context, error handling, interface, module, go test.