A development guide for connecting Python-based plugins to external tool servers through MCP, a standard way for software to expose tools to an AI agent. It covers registering tools, managing connections, passing request context, and tracing calls.

Use it when building or changing Python tool plugins, MCP connections, tool registries, or tracing for tool calls.

It provides rules for keeping shared connections efficient and preventing request-specific data or secrets from leaking between runs.

How extra-org/extra configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to extra-org/extra. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/extra-org/extra/main/.claude/skills/mcp-tools/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/extra-org/extra

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/extra-org/extra/mcp-tools/github.svg)](https://agentmods.dev/skills/extra-org/extra/mcp-tools)

Your own site

<a href="https://agentmods.dev/skills/extra-org/extra/mcp-tools"><img src="https://agentmods.dev/badge/skills/extra-org/extra/mcp-tools/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/extra-org/extra/mcp-tools"><img src="https://agentmods.dev/badge/skills/extra-org/extra/mcp-tools.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 440 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.00036	$0.00440
Opus 5.5	$0.00014	$0.00176
Sonnet 5.5	$0.00007	$0.00088
Haiku 4.5	$0.00004	$0.00044

Measured 2mo ago against content hash f672165c6def, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-tools 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.

.claude/skills/mcp-tools/SKILL.md · 61 lines

What it actually says

Skill: MCP & Tools

When to use this skill

Use this when working on Python plugin tools, MCP server connections, tool invocation, or tool tracing. Primary task: tasks/0007-mcp-tools-and-permissions.md.

Files to read first

AGENTS.md
docs/MCP_AND_TOOLS.md
docs/RUNTIME_LIFECYCLE.md

Architecture rules

Resolver plugins run before a node; tool plugins are exposed to the LLM during execution.
MCP clients are created once and shared; never per request.
Per-request data flows via ExecutionContext / ctx.
Prompt text is not a security boundary.
Secrets never live in YAML; they are redacted in traces.

Implementation rules

Implement tool registry and MCP integration in src/agentplatform/tools.
Load plugin classes once where possible.
Invoke configured class/method references with ctx.
Validate tool and MCP ids during validation/compilation; runtime should use resolved bindings.
Hold MCP clients on the long-lived runtime.

Validation checklist

Tool plugin references load and invoke through the registry.
MCP connections are created once and reused.
Per-request context does not leak through shared state.
Tool/MCP calls are traced with redaction.
Tests cover success and failure with fakes.
make check passes.

Common mistakes to avoid

Recreating MCP connections per request.
Treating resolvers as tools or tools as resolvers.
Skipping trace redaction.
Relying on prompt wording for enforcement.

Changes

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 · 61 lines · 36 tokens per session scan A f672165c6def

Subscribe to this mod's changes

mcp-tools is a skill published in the GitHub repository extra-org/extra (117 stars, last pushed 5d ago), licensed MIT. It adds 36 tokens to every session and 440 once invoked, about $0.0001 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 2026-08-30.

Backend and APIs Building agents agentic agentic-ui ai ai-agents ai-orchestration ai-orchestration-engine

oss-alternatives

Find actively maintained open source alternatives to any paid SaaS tool or commercial API. Use this skill whenever a user mentions wanting to replace, swap out, self-host, or find a free/open source version of a paid tool — including but not limited to tools like Datadog, Algolia, Twilio, Stripe, Auth0, Segment…

tinyfish-io/tinyfish-cookbook · 199 tokens

octopus-architecture

Review system architecture, simplify boundaries, or compare interface designs from repository evidence.

nyldn/claude-octopus · 19 tokens

connector-assistant

A conversation skill for creating and managing connectors, which link external systems such as APIs, remote tool servers, or databases to an agent. It distinguishes these connections from separate agent identities and ordinary tool installations.

DemonDamon/AgenticX · 110 tokens

agenticx-a2a-connector

Guide for using the A2A (Agent-to-Agent) communication protocol in AgenticX including agent discovery, skill invocation, remote agent cards, and distributed agent systems. Use when the user wants agents to communicate with each other, set up distributed agent systems, invoke remote agent skills, or build…

DemonDamon/AgenticX · 73 tokens

agenticx-tool-creator

Guide for creating custom tools in AgenticX including function decorator tools, MCP tool integration, tool registries, and remote tool access. Use when the user wants to create tools for agents, integrate external APIs as tools, build MCP servers, or extend agent capabilities with custom functions.

DemonDamon/AgenticX · 63 tokens

contribute-spec-fix

Fix a broken OpenAPI spec in jentic-public-apis with an OpenAPI Overlay, validate it (spectral lint + idempotency check), and contribute it back via a PR to the community catalog. Falls back to applying the same overlay to the local Jentic registry if the user can't wait for maintainer approval, and closes the loop by…

jentic/jentic-one · 138 tokens

extra: Skill for Claude Code