MCP Server Builder
anthropics/skills
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
Investigate MCP tool availability, discovery, and selection, including controlled adoption evaluations.
Install Evaluate MCP Tool Adoption
$ npx skills add morluto/jacobian --skill evaluate-mcp-tool-adoption -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install morluto/jacobian evaluate-mcp-tool-adoption --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/morluto/jacobian.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/evaluate-mcp-tool-adoption .claude/skills/evaluate-mcp-tool-adoption && rm -rf skills-srcUse ~/.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/
Install the "evaluate-mcp-tool-adoption" agent skill from https://github.com/morluto/jacobian/tree/main/.agents/skills/evaluate-mcp-tool-adoption into .claude/skills/evaluate-mcp-tool-adoption/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "evaluate-mcp-tool-adoption", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/morluto/jacobian/tree/main/.agents/skills/evaluate-mcp-tool-adoptionType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add morluto/jacobian --skill evaluate-mcp-tool-adoption -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install morluto/jacobian evaluate-mcp-tool-adoption --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/morluto/jacobian.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/evaluate-mcp-tool-adoption .agents/skills/evaluate-mcp-tool-adoption && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "evaluate-mcp-tool-adoption" agent skill from https://github.com/morluto/jacobian/tree/main/.agents/skills/evaluate-mcp-tool-adoption into .agents/skills/evaluate-mcp-tool-adoption/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "evaluate-mcp-tool-adoption", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add morluto/jacobian --skill evaluate-mcp-tool-adoption -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install morluto/jacobian evaluate-mcp-tool-adoption --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/morluto/jacobian.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/evaluate-mcp-tool-adoption .cursor/skills/evaluate-mcp-tool-adoption && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "evaluate-mcp-tool-adoption" agent skill from https://github.com/morluto/jacobian/tree/main/.agents/skills/evaluate-mcp-tool-adoption into .cursor/skills/evaluate-mcp-tool-adoption/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "evaluate-mcp-tool-adoption", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/morluto/jacobian.git --path .agents/skills/evaluate-mcp-tool-adoption--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add morluto/jacobian --skill evaluate-mcp-tool-adoption -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install morluto/jacobian evaluate-mcp-tool-adoption --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/morluto/jacobian.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/evaluate-mcp-tool-adoption .gemini/skills/evaluate-mcp-tool-adoption && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "evaluate-mcp-tool-adoption" agent skill from https://github.com/morluto/jacobian/tree/main/.agents/skills/evaluate-mcp-tool-adoption into .gemini/skills/evaluate-mcp-tool-adoption/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "evaluate-mcp-tool-adoption", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install morluto/jacobian evaluate-mcp-tool-adoptionInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add morluto/jacobian --skill evaluate-mcp-tool-adoption -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/morluto/jacobian.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/evaluate-mcp-tool-adoption .github/skills/evaluate-mcp-tool-adoption && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "evaluate-mcp-tool-adoption" agent skill from https://github.com/morluto/jacobian/tree/main/.agents/skills/evaluate-mcp-tool-adoption into .github/skills/evaluate-mcp-tool-adoption/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "evaluate-mcp-tool-adoption", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add morluto/jacobian --skill evaluate-mcp-tool-adoption -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install morluto/jacobian evaluate-mcp-tool-adoption --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/morluto/jacobian.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/evaluate-mcp-tool-adoption .opencode/skills/evaluate-mcp-tool-adoption && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "evaluate-mcp-tool-adoption" agent skill from https://github.com/morluto/jacobian/tree/main/.agents/skills/evaluate-mcp-tool-adoption into .opencode/skills/evaluate-mcp-tool-adoption/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "evaluate-mcp-tool-adoption", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
evaluate-mcp-tool-adoption- GitHub stars
- 220
- Token cost
- ~1k tokens
- SKILL.md length
- 544 words
- Files
- 3 (incl. references)
- Skills in repo
- 11
- Repo updated
- First seen
- Licence
- MIT
At a glance
Investigate MCP tool availability, discovery, and selection, including controlled adoption evaluations.
- Tasks that involve MCP servers
- SKILL.md covers Freeze the question, Establish the four-stage…, When model comparisons are… and Attribute conservatively
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Evaluate MCP Tool Adoption is an agent skill from morluto/jacobian. Investigate MCP tool availability, discovery, and selection, including controlled adoption evaluations.
Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `agents/openai.yaml` and `references/model-comparisons.md`).
It sits in Agent Workflows, covering MCP servers. It works with Model Context Protocol. 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
- “/evaluate-mcp-tool-adoption”
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
Evaluate MCP Tool Adoption loads about 1k tokens when it runs, and up to ~1.5k if it reads all its reference files. Until then it costs about 33 tokens; SKILL.md has 544 words of instructions outside code blocks.
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). 544 words, ~1,021 tokens.
Download SKILL.mdSave it as
.claude/skills/evaluate-mcp-tool-adoption/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.- name
- evaluate-mcp-tool-adoption
- description
- Investigate MCP tool availability, discovery, and selection, including controlled adoption evaluations.
Evaluate MCP Tool Adoption
Evaluate an agent-facing tool as a routing surface, not as a call-count target. Distinguish availability, discovery, selection, and execution before changing server instructions, tool metadata, or the operation contract. Load this skill only for the evaluator; never enable it in an agent-under-test configuration.
Use harbor-benchmarks for a Harbor task or verifier change and
verifier-evaluations for its mathematical verifier. This skill owns only the
adoption diagnosis and its evidence boundary.
Freeze the question
For a controlled comparison, write one falsifiable question, such as “does server-level guidance cause an agent to inspect a matching operation when the ordinary prompt does not?” Keep the model, model version, reasoning effort, client version, Jacobian revision, image digest, task digest, MCP configuration, egress/proxy state, attempt count, and budgets fixed across comparable arms.
Record the relevant prompt and agent-visible MCP surface. In a controlled comparison, do not include an operation ID, answer, or routing instruction in a natural-use arm. Do not score a tool call as success: final mathematical correctness, declared witness validity, and truthful claims remain the task outcomes.
Establish the four-stage control matrix
Run deterministic checks before model calls, then use the smallest set of model arms that distinguishes the suspected stage.
| Stage | Minimal probe | What a pass establishes |
|---|---|---|
| Availability | Start the configured MCP server and inspect the initialization/tool list. | The client receives the intended connection, tools, descriptions, and schemas. |
| Discovery | Search with a natural user phrase and natural category; inspect only returned candidates. | A relevant operation is reachable without prior taxonomy or exact-ID knowledge. |
| Execution | Invoke the known matching operation directly with one frozen valid payload. | Input schema, dispatch, and typed result work. |
| Selection | Give a fresh agent the same mathematical task under no cue, server guidance only, and one clearly labeled task-level routing cue. | The effect of routing/salience is separable from connection and execution. |
Keep the execution control separate from discovery. A direct operation ID can prove dispatch, but cannot prove that an agent would find that operation. Likewise, a task-level instruction can prove that the client can call a tool, but cannot prove that server initialization instructions are salient enough to change ordinary selection.
Show full SKILL.md (188 more words)Show less
When model comparisons are needed
Use model comparisons for controlled arms, event capture, and scoring. Run only the arms needed to answer the frozen question within user-authorized cost boundaries. A deterministic diagnosis does not require a model experiment.
Attribute conservatively
Use the smallest supported conclusion:
- A missing session, missing tool, or changed schema is an availability or presentation failure.
- A direct call succeeding while natural search misses the operation is a discovery/taxonomy problem.
- A direct-call control succeeding while uncued agents avoid the tool is a selection or salience observation, not proof that initialization guidance is absent from the model context.
- A task-level cue changing behavior proves that the cue can route behavior; it does not show that the call improved correctness or should become mandatory.
- Invalid typed input or output belongs to the operation contract or transport boundary, not to agent adoption.
Use at least one repeated or independently varied case before claiming a stable effect. Open an issue only with the exact prompt, environment, event evidence, and the distinction between verified behavior and the remaining hypothesis. Keep outcome evaluation separate from telemetry intended to explain tool selection.
© 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 2 other files (references) in .agents/skills/evaluate-mcp-tool-adoption of morluto/jacobian.
- SKILL.md
- agents/openai.yaml
- references/model-comparisons.md
Open the folder on GitHubat commit 9dc2aaf
Compare with similar skills
Evaluate MCP Tool Adoption 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Evaluate MCP Tool Adoption this skillmorluto/jacobian | 220 | — | ~1k | Automated safety check: Pass | MIT | |
| MCP Server Builderanthropics/skills | 180k | 63 repos | ~2.3k | Automated safety check: Pass | Apache-2.0 | |
| MCP Server BuildershareAI-lab/learn-claude-code | 78k | 4 repos | ~1.2k | Automated safety check: Pass | MIT | |
| MCP Integration for Pluginsanthropics/claude-plugins-official | 38k | 11 repos | ~3.1k | Automated safety check: Pass | Apache-2.0 | |
| Crush Configurationcharmbracelet/crush | 29k | — | ~3.7k | Automated safety check: Pass | Custom licence | |
| Context Mode Output Sandboxmksglu/context-mode | 26k | — | ~4.1k | Automated safety check: Pass | Custom licence |
Similar skills
- Official
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.
- Official
MCP Integration for Plugins
anthropics/claude-plugins-official
Explains how to bundle Model Context Protocol servers in a Claude Code plugin, covering config files, stdio, SSE, HTTP and WebSocket server types, and authentication.
Crush Configuration
charmbracelet/crush
Explains how to configure the Crush coding agent with crushrc or crush.json, covering providers, models, LSPs, MCP servers, hooks, permissions and config precedence.
Context Mode Output Sandbox
mksglu/context-mode
Routes large command, file, API and browser output through context-mode tools so only the needed result enters the agent's context, instead of dumping it via Bash.
Warp GUI to Agent CLI Migration
warpdotdev/warp
Migrates the compatible subset of settings and global file-based MCP servers from the Warp desktop app into Warp Agent CLI without exposing credentials or state.
More from morluto/jacobian
All 11 skills in this repoRecent Conjecture Evaluations
morluto/jacobian
Evaluate Jacobian reliability using recently resolved conjectures as held-out probes.
Harbor Benchmarks
morluto/jacobian
Author, package, validate, or run mathematical evaluations as Jacobian Harbor datasets.
Audit Public Operation Contracts
morluto/jacobian
Design or audit a Jacobian operation’s mathematical contract, boundedness, exact results, and composition.
Decompose Mathematical Solution Corpora
morluto/jacobian
Extract reusable Jacobian capabilities from a mathematical solution corpus, rather than one agent trajectory.
Learn From Math Agent Trajectories
morluto/jacobian
Review mathematical agent trajectories for evidence-backed Jacobian improvements; do not resume solving.
Verifier Evaluations
morluto/jacobian
Design, audit, or repair mathematical benchmark verifiers, submission contracts, and scoring.
Related
Works with
Categories
Questions about Evaluate MCP Tool Adoption
What does Evaluate MCP Tool Adoption do?
Investigate MCP tool availability, discovery, and selection, including controlled adoption evaluations. Evaluate MCP Tool Adoption is an agent skill from morluto/jacobian. Investigate MCP tool availability, discovery, and selection, including controlled adoption evaluations.
When should I use Evaluate MCP Tool Adoption?
Evaluate MCP Tool Adoption fits situations like: tasks that involve MCP servers.
How do I install Evaluate MCP Tool Adoption in Claude Code?
Run `npx skills add morluto/jacobian --skill evaluate-mcp-tool-adoption -a claude-code`. Or copy the skill folder (.agents/skills/evaluate-mcp-tool-adoption in morluto/jacobian) into .claude/skills/evaluate-mcp-tool-adoption in your project. Claude Code loads it when a task matches its description.
How do I install Evaluate MCP Tool Adoption in Codex?
Run `npx skills add morluto/jacobian --skill evaluate-mcp-tool-adoption -a codex`. Or copy the skill folder (.agents/skills/evaluate-mcp-tool-adoption in morluto/jacobian) into .agents/skills/evaluate-mcp-tool-adoption in your project. Codex loads it when a task matches its description.
Can I use Evaluate MCP Tool Adoption 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 evaluate-mcp-tool-adoption -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/evaluate-mcp-tool-adoption, .gemini/skills/evaluate-mcp-tool-adoption, .github/skills/evaluate-mcp-tool-adoption and .opencode/skills/evaluate-mcp-tool-adoption in your project.
What does Evaluate MCP Tool Adoption need to run?
SKILL.md names no scripts, command-line tools or credentials: Evaluate MCP Tool Adoption is instructions for the agent only.
Does Evaluate MCP Tool Adoption 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 Evaluate MCP Tool Adoption 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 Evaluate MCP Tool Adoption use?
Evaluate MCP Tool Adoption 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 Evaluate MCP Tool Adoption use?
About 1k tokens (SKILL.md is roughly 4.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 433 tokens, read only when the agent opens those files.
What are the alternatives to Evaluate MCP Tool Adoption?
Skills that share tags, products or a category with Evaluate MCP Tool Adoption: MCP Server Builder (anthropics/skills, 180k stars), MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars), MCP Integration for Plugins (anthropics/claude-plugins-official, 38k stars) and Crush Configuration (charmbracelet/crush, 29k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Evaluate MCP Tool Adoption?
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.