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 pincerhq/pincer --skill mcp-server-setupgit clone --depth 1 https://github.com/pincerhq/pincerWrote 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/pincerhq/pincer/mcp-server-setup)<a href="https://agentmods.dev/skills/pincerhq/pincer/mcp-server-setup"><img src="https://agentmods.dev/badge/skills/pincerhq/pincer/mcp-server-setup/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/pincerhq/pincer/mcp-server-setup"><img src="https://agentmods.dev/badge/skills/pincerhq/pincer/mcp-server-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00054 | $0.00556 |
| Opus 5 | $0.00027 | $0.00278 |
| Sonnet 5 | $0.00011 | $0.00111 |
| Haiku 4.5 | $0.00005 | $0.00056 |
Grade A, and why
MCP server setup 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 9d 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP server setup
Pincer is both an MCP client (connects to external MCP servers like GitHub, Slack, Postgres, filesystem, browser automation) and an MCP server (exposes Pincer's own tools to external MCP clients via OAuth 2.0). Skills and MCP servers now coexist — connecting an MCP server does not disable skills.
Connecting an external MCP server (client mode)
- Install the optional extra:
uv pip install "pincer-agent[mcp]". - Add a
[[mcp.servers]]block topincer.toml(or the equivalent env vars) with the server's name, transport (stdio/SSE/HTTP), command or URL, and any required auth (API key, OAuth token). - Restart the agent (
pincer run). On startup you'll seeMCP '<name>' connectedor afailed to connectwarning in the console — check that message first if something's wrong. - MCP tools appear in the agent's tool list identically to built-in tools; the LLM calls them the same way, with the same approval flow.
For the full config reference (transports, auth schemes, scopes, examples
for popular servers), load the detailed guide at
docs/guides/mcp-guide.md in the repository, or reference it via
load_skill_reference if it's bundled alongside this skill.
Exposing Pincer as an MCP server
Pincer's own tools can be exposed to external MCP clients (Claude Desktop,
other agents) via OAuth 2.0 with PKCE and scope-based access control.
Which tools are exposed by default is controlled by an expose_tools
allowlist in the MCP config — read-only tools are typically exposed by
default, execute/write tools are opt-in.
Troubleshooting
- "MCP config load failed" at startup: check
pincer.tomlsyntax — the agent falls back to running without MCP rather than crashing. - A server shows connected but its tools aren't callable: check the server's own scope/permission settings, not just Pincer's config.
- Too many tools registered (>100 from one server): the agent warns that LLM tool selection may degrade — consider filtering which tools that server exposes.
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.
- 9d ago First seen · 48 lines · 54 tokens per session scan A 323de755531a
MCP server setup is a skill published in the GitHub repository pincerhq/pincer (50 stars, last pushed yesterday), licensed MIT. It adds 54 tokens to every session and 556 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…