New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Audit MCP Tool Friction

by morluto in morluto/jacobian

Diagnose malformed calls, retries, and unusable results after an agent selects an MCP tool.

MITAuto-check passedAgent Workflows

Install Audit MCP Tool Friction

skills CLI
$ npx skills add morluto/jacobian --skill audit-mcp-tool-friction -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install morluto/jacobian audit-mcp-tool-friction --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/morluto/jacobian.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/audit-mcp-tool-friction .claude/skills/audit-mcp-tool-friction && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
audit-mcp-tool-friction
GitHub stars
220
Token cost
~1.1k tokens
SKILL.md length
609 words
Files
2
Skills in repo
11
Repo updated
First seen
Licence
MIT

At a glance

Diagnose malformed calls, retries, and unusable results after an agent selects an MCP tool.

  • Tasks that involve MCP servers
  • SKILL.md covers Set the boundary, Inspect the public contract, Read a trace as a recovery… and Measure benchmark friction, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Audit MCP Tool Friction is an agent skill from morluto/jacobian. Diagnose malformed calls, retries, and unusable results after an agent selects an MCP tool.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It sits in Agent Workflows, covering MCP servers. It works with Model Context Protocol and Python. The repository describes itself as: Composable mathematics tools for agents. The licence is MIT.

When your agent uses it

  • Tasks that involve MCP servers

Example prompts

  • “/audit-mcp-tool-friction”

Requirements

  • Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit 9dc2aaf. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Audit MCP Tool Friction loads about 1.1k tokens when it runs. Until then it costs about 29 tokens; SKILL.md has 609 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~29
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from morluto/jacobian at commit 9dc2aaf, republished under its MIT licence (© morluto). 609 words, ~1,125 tokens.

Download SKILL.mdSave it as .claude/skills/audit-mcp-tool-friction/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
audit-mcp-tool-friction
description
Diagnose malformed calls, retries, and unusable results after an agent selects an MCP tool.

Audit MCP Tool Friction

Audit whether an agent that has chosen a tool can form a valid request, recover from a failure, and use the returned value. This is a public-contract audit, not a call-count target and not a test of model willingness to use a tool.

Set the boundary

Record the tool, revision, client, task or trace, and public inputs inspected. Keep these questions separate:

  • Adoption: whether the agent saw, discovered, or selected a tool.
  • Friction: whether the selected tool made its contract, valid input, error recovery, and result use clear enough to execute correctly.
  • Capability: whether an operation actually covers the requested work.

Do not call a successful Python fallback evidence that a tool contract is easy to use. Do not call a single malformed request a product defect without checking what the public contract exposed beforehand.

Inspect the public contract

For each relevant operation, inspect the generated MCP input and output schemas, tool description, discovery/inspection result, operation examples, and error messages. Trace every non-obvious requirement to its owner:

Contract elementCheck
Input expressionRequired values, units, encodings, ordering, and bounds are visible before the call.
Schema projectionConstraints representable in JSON Schema appear there with useful field descriptions and examples.
Semantic validationRules enforced only by a model validator have an explicit description and minimal valid example.
RecoveryErrors identify the field and state the smallest concrete correction.
Result useResult shape, exactness, limits, and reconstruction information let the caller continue without guessing.

Pydantic does not infer JSON-Schema descriptions or examples from custom model validators. Add Field(description=..., examples=...) or appropriate json_schema_extra when a semantic invariant cannot be encoded as a standard JSON-Schema constraint. Keep canonical output rules when they support stable composition; improve the input guidance before weakening the invariant.

Show full SKILL.md (316 more words)Show less

Read a trace as a recovery journey

Capture the exact operation ID, first payload, typed result or error, retry, and final use of the value. Classify the first failure narrowly:

  • Hidden representation rule: required ordering, encoding, or cross-field relation was not visible in the public contract.
  • Insufficient example or description: the rule was technically present but not concrete enough for an ordinary first request.
  • Unhelpful recovery: the error lacks a field, cause, or actionable repair.
  • Tool or transport defect: a documented valid request fails, result schema is wrong, or the typed result cannot be consumed as declared.
  • Agent slip: the contract and recovery path were clear; one isolated malformed call does not establish a product problem.

Compare a direct known-valid execution separately from the trace. A direct pass proves the operation works; it does not erase caller friction. A trace with no call is out of scope unless availability or adoption is under review.

Measure benchmark friction

For comparable runs, freeze task, image, server revision, model, client, budget, and MCP configuration. Report final verifier outcome separately from:

  • first-call validity;
  • operation inspection before execution;
  • validation failures by field and invariant;
  • recovery attempts and whether a retry used the returned error;
  • typed-result use versus manual fallback; and
  • added calls, tokens, and elapsed time.

Use repeated tasks or attempts before claiming a stable rate. A successful answer after retries is evidence of recoverability, not evidence of a frictionless interface.

Recommend the smallest repair

Prefer, in order: clearer field metadata and examples; actionable errors; schema-level constraints; a narrowly scoped adapter or helper. Normalize input only when it preserves the documented mathematical meaning and does not hide ambiguity, duplicate terms, or caller mistakes. Preserve bounded operation semantics and return values directly.

Report confirmed behavior, the exact public evidence, the affected stage, proportionate repair, and what remains untested. State when the evidence only supports an agent slip rather than a tool-design finding.

© morluto, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in .agents/skills/audit-mcp-tool-friction of morluto/jacobian.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit 9dc2aaf

Compare with similar skills

Audit MCP Tool Friction next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Audit MCP Tool Friction compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Audit MCP Tool Friction this skillmorluto/jacobian220—~1.1kAutomated safety check: PassMIT
MCP Server Builderanthropics/skills180k63 repos~2.3kAutomated safety check: PassApache-2.0
MCP Server BuildershareAI-lab/learn-claude-code78k4 repos~1.2kAutomated safety check: PassMIT
MemPalace Setup and OperationMemPalace/mempalace60k—~2.2kAutomated safety check: PassMIT
FastmcpTommy-yw/RunbookHermes5463 repos~2.1kAutomated safety check: PassMIT
Fastmcp Client CLIPrefectHQ/fastmcp28k—~823Automated safety check: PassApache-2.0

Similar skills

  • MCP Server Builder

    anthropics/skills

    Official

    Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.

    180k GitHub starsUsed in 63 repos~2.3k tokens
    Agent WorkflowsAuto-check passed

  • MCP Server Builder

    shareAI-lab/learn-claude-code

    Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.

    78k GitHub starsUsed in 4 repos~1.2k tokens
    Agent WorkflowsAuto-check passed

  • MemPalace Setup and Operation

    MemPalace/mempalace

    Installs and configures MemPalace as a private local palace, a shared-brain hub or a client of an existing hub, including MCP registration and version-correct initialization.

    60k GitHub stars~2.2k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Fastmcp

    Tommy-yw/RunbookHermes

    Build, test, inspect, install, and deploy MCP servers with FastMCP in Python.

    546 GitHub starsUsed in 3 repos~2.1k tokens
    Agent WorkflowsAuto-check passed

  • Fastmcp Client CLI

    PrefectHQ/fastmcp

    Query and invoke tools on MCP servers using fastmcp list and fastmcp call.

    28k GitHub stars~823 tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

  • Migrate To Archestra

    archestra-ai/archestra

    Migrate an existing agentic PoC/pilot (Claude Code project files, MCP configs, hooks, local tools, openclaw config, or similar hand-rolled setup artifacts) into an Archestra instance.

    4.4k GitHub stars~2.5k tokensUpdated today
    Agent WorkflowsAuto-check passed

More from morluto/jacobian

All 11 skills in this repo

  • Recent Conjecture Evaluations

    morluto/jacobian

    Evaluate Jacobian reliability using recently resolved conjectures as held-out probes.

    220 GitHub stars~816 tokensUpdated 6 days ago
    Auto-check passed

  • Harbor Benchmarks

    morluto/jacobian

    Author, package, validate, or run mathematical evaluations as Jacobian Harbor datasets.

    220 GitHub stars~690 tokensUpdated 6 days ago
    Auto-check passed

  • Audit Public Operation Contracts

    morluto/jacobian

    Design or audit a Jacobian operation’s mathematical contract, boundedness, exact results, and composition.

    220 GitHub stars~2k tokensUpdated 6 days ago
    Auto-check passed

  • Decompose Mathematical Solution Corpora

    morluto/jacobian

    Extract reusable Jacobian capabilities from a mathematical solution corpus, rather than one agent trajectory.

    220 GitHub stars~1.9k tokensUpdated 6 days ago
    Auto-check passed

  • Evaluate MCP Tool Adoption

    morluto/jacobian

    Investigate MCP tool availability, discovery, and selection, including controlled adoption evaluations.

    220 GitHub stars~1k tokensUpdated 6 days ago
    Auto-check passed

  • Learn From Math Agent Trajectories

    morluto/jacobian

    Review mathematical agent trajectories for evidence-backed Jacobian improvements; do not resume solving.

    220 GitHub stars~848 tokensUpdated 6 days ago
    Auto-check passed

Works with

Categories

Questions about Audit MCP Tool Friction

What does Audit MCP Tool Friction do?

Diagnose malformed calls, retries, and unusable results after an agent selects an MCP tool. Audit MCP Tool Friction is an agent skill from morluto/jacobian. Diagnose malformed calls, retries, and unusable results after an agent selects an MCP tool.

When should I use Audit MCP Tool Friction?

Audit MCP Tool Friction fits situations like: tasks that involve MCP servers.

How do I install Audit MCP Tool Friction in Claude Code?

Run `npx skills add morluto/jacobian --skill audit-mcp-tool-friction -a claude-code`. Or copy the skill folder (.agents/skills/audit-mcp-tool-friction in morluto/jacobian) into .claude/skills/audit-mcp-tool-friction in your project. Claude Code loads it when a task matches its description.

How do I install Audit MCP Tool Friction in Codex?

Run `npx skills add morluto/jacobian --skill audit-mcp-tool-friction -a codex`. Or copy the skill folder (.agents/skills/audit-mcp-tool-friction in morluto/jacobian) into .agents/skills/audit-mcp-tool-friction in your project. Codex loads it when a task matches its description.

Can I use Audit MCP Tool Friction in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add morluto/jacobian --skill audit-mcp-tool-friction -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/audit-mcp-tool-friction, .gemini/skills/audit-mcp-tool-friction, .github/skills/audit-mcp-tool-friction and .opencode/skills/audit-mcp-tool-friction in your project.

What does Audit MCP Tool Friction need to run?

SKILL.md names no scripts, command-line tools or credentials: Audit MCP Tool Friction is instructions for the agent only. Our summary lists: Python 3.

Does Audit MCP Tool Friction access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Audit MCP Tool Friction safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Audit MCP Tool Friction use?

Audit MCP Tool Friction is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Audit MCP Tool Friction use?

About 1.1k tokens (SKILL.md is roughly 4.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Audit MCP Tool Friction?

Skills that share tags, products or a category with Audit MCP Tool Friction: MCP Server Builder (anthropics/skills, 180k stars), MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars), MemPalace Setup and Operation (MemPalace/mempalace, 60k stars) and Fastmcp (Tommy-yw/RunbookHermes, 546 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Audit MCP Tool Friction?

morluto (a GitHub user) maintains it in morluto/jacobian, which has 220 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on October 5, 2026.

Source: morluto/jacobian on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.