Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add ishandutta2007/Awesome-Agent-Skills --skill mcp-tool-integrationgit clone --depth 1 https://github.com/ishandutta2007/Awesome-Agent-SkillsWrote 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/skills/ishandutta2007/awesome-agent-skills/mcp-tool-integration)<a href="https://agentmods.dev/skills/ishandutta2007/awesome-agent-skills/mcp-tool-integration"><img src="https://agentmods.dev/badge/skills/ishandutta2007/awesome-agent-skills/mcp-tool-integration/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/skills/ishandutta2007/awesome-agent-skills/mcp-tool-integration"><img src="https://agentmods.dev/badge/skills/ishandutta2007/awesome-agent-skills/mcp-tool-integration.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 | $0.00037 | $0.00410 |
| Opus 5 | $0.00018 | $0.00205 |
| Sonnet 5 | $0.00007 | $0.00082 |
| Haiku 4.5 | $0.00004 | $0.00041 |
Grade A, and why
mcp-tool-integration 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 11d 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
MCP Tool Integration
Overview
Model Context Protocol (MCP) is the standard for connecting AI agents to external tools and context. This skill guides the integration and development of new MCP tools.
When to Use
- You need to access data outside the agent's current context
- You are building custom tools for Claude Desktop or other MCP-compatible clients
- Integrating REST APIs, databases, or local services via MCP
Process
- Define the Protocol: Choose standard stdio or SSE depending on the deployment environment.
- Design Tool Schemas: Create clear, descriptive JSON schemas for tool inputs.
- Implement Handlers: Write the execution logic.
- Test Locally: Verify tool execution and error handling.
- Configure Client: Add the MCP server to the agent's configuration file.
Common Rationalizations
| Rationalization | Why It Is Wrong |
|---|---|
| "The handler works, so the tool is done." | Agents rely on schemas, names, and descriptions as much as handler code. |
| "Errors can just throw." | MCP clients need predictable errors so agents can recover or explain the failure. |
| "The client config is obvious." | A working server is not useful until the target client can discover and invoke it. |
Red Flags
- Tool names or descriptions are vague
- Inputs accept broad strings instead of structured fields
- The handler returns raw internal errors or stack traces
- No local client invocation has been tested
Verification
Before finishing, confirm:
- Tool schemas describe the inputs an agent should actually provide
- Handler success and error paths were exercised locally
- Client configuration is documented and tested
- Secrets, tokens, and local paths are not exposed in tool responses
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.
- 11d ago First seen · 46 lines · 37 tokens per session scan A 8fb1df5ad475
mcp-tool-integration is a skill published in the GitHub repository ishandutta2007/Awesome-Agent-Skills (21 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 410 once invoked, about $0.0002 per session on Opus 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 2026-08-30.
Other skills, from other repositories
hunt-auth-bypass
Hunting skill for auth bypass vulnerabilities. Built from 4 public bug bounty reports. Use when hunting auth bypass on any target.
hunt-xxe
Hunting skill for xxe vulnerabilities. Built from 4 public bug bounty reports. Use when hunting xxe on any target.
hunt-graphql
Hunting skill for graphql vulnerabilities. Built from 3 public bug bounty reports. Use when hunting graphql on any target.
hunt-idor
Hunting skill for idor vulnerabilities. Built from 26 public bug bounty reports. Use when hunting idor on any target.
hunt-http-smuggling
Hunt HTTP request smuggling (CL.TE, TE.CL, H2.CL, H2.TE). Cause: front-end proxy and back-end server disagree on where one request ends and the next begins (Content-Length vs Transfer-Encoding header parsing inconsistency). CL.TE: front-end uses CL, back uses TE → smuggle by sending TE: chunked but with body that fits…
hunt-api-misconfig
Hunt API security misconfiguration — mass assignment, JWT attacks, prototype pollution, CORS, HTTP verb tampering. Mass assignment: send {isadmin:true, role:admin, verified:true} on profile/account/reset endpoints — server blindly applies. JWT: alg=none, weak HMAC bruteforce, kid path traversal, JWK injection, token…