MCP Server Builder with mcp-use
mcp-use/mcp-use
Builds, modifies, debugs, migrates and verifies TypeScript MCP servers and MCP Apps with the mcp-use framework, treating the installed package's types as the source of truth.
A skill your agent uses when asked to expose a folder of notes or docs to Claude or another AI client, build an MCP server over Markdown or JSON files, let an agent read my knowledge base safely, or…
Install Readonly MCP Wrapper
$ npx skills add mohitagw15856/pm-claude-skills --skill readonly-mcp-wrapper -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install mohitagw15856/pm-claude-skills readonly-mcp-wrapper --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/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/readonly-mcp-wrapper .claude/skills/readonly-mcp-wrapper && 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 "readonly-mcp-wrapper" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/readonly-mcp-wrapper into .claude/skills/readonly-mcp-wrapper/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "readonly-mcp-wrapper", 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/mohitagw15856/pm-claude-skills/tree/main/skills/readonly-mcp-wrapperType 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 mohitagw15856/pm-claude-skills --skill readonly-mcp-wrapper -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install mohitagw15856/pm-claude-skills readonly-mcp-wrapper --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/readonly-mcp-wrapper .agents/skills/readonly-mcp-wrapper && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "readonly-mcp-wrapper" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/readonly-mcp-wrapper into .agents/skills/readonly-mcp-wrapper/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "readonly-mcp-wrapper", 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 mohitagw15856/pm-claude-skills --skill readonly-mcp-wrapper -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install mohitagw15856/pm-claude-skills readonly-mcp-wrapper --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/readonly-mcp-wrapper .cursor/skills/readonly-mcp-wrapper && 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 "readonly-mcp-wrapper" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/readonly-mcp-wrapper into .cursor/skills/readonly-mcp-wrapper/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "readonly-mcp-wrapper", 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/mohitagw15856/pm-claude-skills.git --path skills/readonly-mcp-wrapper--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 mohitagw15856/pm-claude-skills --skill readonly-mcp-wrapper -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install mohitagw15856/pm-claude-skills readonly-mcp-wrapper --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/readonly-mcp-wrapper .gemini/skills/readonly-mcp-wrapper && 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 "readonly-mcp-wrapper" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/readonly-mcp-wrapper into .gemini/skills/readonly-mcp-wrapper/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "readonly-mcp-wrapper", 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 mohitagw15856/pm-claude-skills readonly-mcp-wrapperInstalls 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 mohitagw15856/pm-claude-skills --skill readonly-mcp-wrapper -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/readonly-mcp-wrapper .github/skills/readonly-mcp-wrapper && 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 "readonly-mcp-wrapper" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/readonly-mcp-wrapper into .github/skills/readonly-mcp-wrapper/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "readonly-mcp-wrapper", 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 mohitagw15856/pm-claude-skills --skill readonly-mcp-wrapper -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install mohitagw15856/pm-claude-skills readonly-mcp-wrapper --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/readonly-mcp-wrapper .opencode/skills/readonly-mcp-wrapper && 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 "readonly-mcp-wrapper" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/readonly-mcp-wrapper into .opencode/skills/readonly-mcp-wrapper/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "readonly-mcp-wrapper", 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
readonly-mcp-wrapper- GitHub stars
- 1.4k
- Token cost
- ~1.3k tokens
- SKILL.md length
- 650 words
- Files
- 2 (incl. references)
- Skills in repo
- 1,348
- Repo updated
- First seen
- Licence
- MIT
At a glance
A skill your agent uses when asked to expose a folder of notes or docs to Claude or another AI client, build an MCP server over Markdown or JSON files, let an agent read my knowledge base safely, or…
- Works in 5 steps: Server code → Tool definitions → Client configuration → …
- Asked to expose a folder of notes
- SKILL.md covers Required Inputs, Output Structure, Quality Checks and Anti-Patterns, plus 1 more section
- Runs JavaScript scripts from its folder; calls claude
What it does
Readonly MCP Wrapper is an agent skill from mohitagw15856/pm-claude-skills. Use when asked to expose a folder of notes or docs to Claude or another AI client, build an MCP server over Markdown or JSON files, let an agent read my knowledge base safely, or wrap documentation as MCP tools. Produces a read-only MCP server over a folder of Markdown or JSON files: server code using stdio transport, tool definitions, a client configuration snippet, and a safety section confirming no write, delete or network tools are exposed. To design an MCP server for a whole product, use mcp-server-spec.
Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files.
It sits in Agent Workflows, covering MCP servers and Structured output and tool calling. It works with Model Context Protocol. The repository describes itself as: 1255 professional Agent Skills for Claude, ChatGPT, Gemini, Cursor & Codex — PRDs, postmortems, leases, medical bills, layoffs, go-bags, new countries. Plain markdown, MIT, in… The licence is MIT.
When your agent uses it
- Asked to expose a folder of notes
- Another AI client
- Build an MCP server over Markdown
- Let an agent read my knowledge base safely
Example prompts
- “/readonly-mcp-wrapper”
Requirements
- Python 3
- Node.js
Workflow steps
5 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 1cbf1f0. 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
Ships script files (JavaScript), which the agent can run.
Shell commands in SKILL.md call:
claude
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
Readonly MCP Wrapper loads about 1.3k tokens when it runs, and up to ~2.7k if it reads all its reference files. Until then it costs about 134 tokens; SKILL.md has 650 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: notes
The automated check noted patterns worth knowing about, such as sudo or a known installer.
- NoteMentions a .env fileSKILL.md:76
lder.** Allow-list file types; keys and `.env` files live in the same trees as docs.
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 mohitagw15856/pm-claude-skills at commit 1cbf1f0, republished under its MIT licence (© mohitagw15856). 650 words, ~1,266 tokens.
Download SKILL.mdSave it as
.claude/skills/readonly-mcp-wrapper/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- readonly-mcp-wrapper
- description
- Use when asked to expose a folder of notes or docs to Claude or another AI client, build an MCP server over Markdown or JSON files, let an agent read my knowledge base safely, or wrap documentation as MCP tools. Produces a read-only MCP server over a folder of Markdown or JSON files: server code using stdio transport, tool definitions, a client configuration snippet, and a safety section confirming no write, delete or network tools are exposed. To design an MCP server for a whole product, use mcp-server-spec.
- version
- 1.0.0
Read-only MCP Wrapper
The fastest way to give an AI assistant a project's knowledge (docs, notes, specs, exported data) is a small MCP server that can list, search and read files, and can do nothing else. Most hand-rolled servers drift into risk: a "helpful" write tool, a path that escapes the folder through .. or a symlink, or logs printed to stdout that corrupt the protocol. This skill generates a server that is read-only by construction, from the tested template in references/server-template.mjs.
Required Inputs
Ask for these if not provided:
- The folder to serve, and roughly how many files and how large
- File types: Markdown, JSON, or both (other types are excluded by default)
- The client: Claude Code, Claude Desktop, Cursor, or another MCP client
- Runtime: Node is the default; ask if the user needs Python instead
- Anything inside the folder that must never be served (drafts, private notes), to exclude by path
Output Structure
1. Server code
A complete file based on references/server-template.mjs, adapted to the inputs:
- stdio transport: newline-delimited JSON-RPC 2.0 on stdin and stdout; all logging on stderr
- handles
initialize,ping,tools/listandtools/call; ignores notifications; returns-32601for anything else - the served root resolved once with
realpath; every requested path resolved and checked to stay inside it, so..and symlinks cannot escape - an allow-list of extensions and a per-file size cap
- exclusions from the inputs applied in the file walk
2. Tool definitions
A table and the JSON schemas:
| Tool | Input | Returns | Read-only hint |
|---|---|---|---|
list_documents | none | relative paths | true |
search_documents | query (2+ characters), optional limit up to 50 | path and excerpt per match | true |
read_document | path from list_documents | full text | true |
Errors are returned as tool results with isError: true and a message that never includes the absolute path.
3. Client configuration
The exact snippet for the named client, with an absolute path placeholder, for example for Claude Code:
claude mcp add my-docs -- node /absolute/path/server.mjs /absolute/path/to/folderand the mcpServers JSON block for Claude Desktop or Cursor.
4. Safety section
A short statement the user can paste into their README, confirming:
- the server exposes exactly three tools, all read-only
- there is no code that writes, deletes, renames or moves files
- there is no network code: no HTTP client, no sockets, no child processes
- paths cannot escape the served folder, including through symlinks
- only allow-listed file types under the size cap are returned
Then the commands that prove it: a grep over the server for write, delete, network and process APIs that should return nothing, and the test below.
Show full SKILL.md (237 more words)Show less
5. Test script
Piped JSON-RPC requests that check: initialize succeeds; the three tools are listed; a document can be listed, searched and read; ../ traversal is refused; a symlink pointing outside is refused; a disallowed extension is refused; an unknown tool returns an error.
Quality Checks
- Exactly three tools are exposed, each with
readOnlyHint: true - The server contains no write, delete, rename, network or child-process calls
- Nothing but protocol messages is written to stdout
- Traversal with
..and symlinks pointing outside the folder are both refused - Only allow-listed extensions under the size cap are served
- Error messages never reveal the absolute path of the served folder
- The client snippet uses absolute paths and the exact command for the named client
- The test script covers every refusal case listed above
Anti-Patterns
- "Just one write tool." The moment an agent can write, the safety story changes; build a separate server for that.
console.logfor debugging. It corrupts the stdio protocol; log to stderr.- Checking paths with string prefixes only.
startsWith(root)withoutrealpathlets symlinks escape. - Serving everything in the folder. Allow-list file types; keys and
.envfiles live in the same trees as docs.
Example Trigger Phrases
- "Make an MCP server so Claude can read my Obsidian notes, read-only."
- "Expose this docs folder to Cursor as MCP tools."
- "Build a safe MCP server over a folder of JSON files."
- "I want my agent to search our specs but never change them."
© mohitagw15856, 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 (references) in skills/readonly-mcp-wrapper of mohitagw15856/pm-claude-skills.
- SKILL.md
- references/server-template.mjs
Open the folder on GitHubat commit 1cbf1f0
Compare with similar skills
Readonly MCP Wrapper 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 |
|---|---|---|---|---|---|---|
| Readonly MCP Wrapper this skillmohitagw15856/pm-claude-skills | 1.4k | — | ~1.3k | Automated safety check: Notes | MIT | |
| MCP Server Builder with mcp-usemcp-use/mcp-use | 11k | — | ~923 | Automated safety check: Pass | Apache-2.0 | |
| Documentation Serverandrea9293/mcp-documentation-server | 343 | — | ~2.3k | Automated safety check: Pass | MIT | |
| MCP Auditgetsentry/toolkit | 918 | — | ~1.5k | Automated safety check: Pass | Custom licence | |
| MCP Server Builderborghei/Claude-Skills | 886 | — | ~1.9k | Automated safety check: Pass | MIT | |
| Spring AI MCP Server Patternsgiuseppe-trisciuoglio/developer-kit | 356 | — | ~2.7k | Automated safety check: Notes | MIT |
Similar skills
Documentation Server
andrea9293/mcp-documentation-server
A skill your agent uses when you need to store, retrieve, search, or manage documents in a local knowledge base with semantic search and hybrid (vector + full-text) retrieval.
- Official
MCP Audit
getsentry/toolkit
Audit MCP servers for protocol compliance, metadata drift, and compatibility regressions.
MCP Server Builder
borghei/Claude-Skills
Build MCP (Model Context Protocol) servers with tool definitions, resource providers, prompt templates, and transports.
Spring AI MCP Server Patterns
giuseppe-trisciuoglio/developer-kit
Provides Spring Boot MCP server patterns that create Model Context Protocol servers with Spring AI by defining tool handlers, exposing resources, configuring prompt templates, and setting up…
Agent Tool Builder
omer-metin/skills-for-antigravity
Tools are how AI agents interact with the world. An agent skill from omer-metin/skills-for-antigravity.
More from mohitagw15856/pm-claude-skills
All 1,348 skills in this repoCar Tco
mohitagw15856/pm-claude-skills
Compare the total cost of car ownership across buy-new, buy-used, lease, and keep-your-current-car — depreciation, insurance, maintenance ramp, and fuel over a real horizon, not just the monthly…
Cs Health Scorecard
mohitagw15856/pm-claude-skills
Build a customer health scorecard for a specific account. An agent skill from mohitagw15856/pm-claude-skills.
Exit Waterfall
mohitagw15856/pm-claude-skills
Compute who gets what at each exit price from a cap table — liquidation preferences, conversion points, and where the founders' share collapses.
Feature Prioritisation
mohitagw15856/pm-claude-skills
Apply prioritisation frameworks (RICE, MoSCoW, Kano, ICE, Opportunity Scoring) to rank features and backlog items.
Fire Number
mohitagw15856/pm-claude-skills
Compute a financial-independence (FIRE) target and years-to-reach with every assumption labeled as an assumption — plus a sensitivity table instead of a single false-precision answer.
Freelance Rate
mohitagw15856/pm-claude-skills
Derive a freelance day/hourly rate backwards from target income, honest billable utilization, overhead, and the self-employment tax premium — the arithmetic that proves a rate is not salary÷2000.
Related
Works with
Categories
Questions about Readonly MCP Wrapper
What does Readonly MCP Wrapper do?
A skill your agent uses when asked to expose a folder of notes or docs to Claude or another AI client, build an MCP server over Markdown or JSON files, let an agent read my knowledge base safely, or…. Readonly MCP Wrapper is an agent skill from mohitagw15856/pm-claude-skills. Use when asked to expose a folder of notes or docs to Claude or another AI client, build an MCP server over Markdown or JSON files, let an agent read my knowledge base safely, or wrap documentation as MCP tools.
When should I use Readonly MCP Wrapper?
Readonly MCP Wrapper fits situations like: asked to expose a folder of notes; another AI client; build an MCP server over Markdown; let an agent read my knowledge base safely.
How do I install Readonly MCP Wrapper in Claude Code?
Run `npx skills add mohitagw15856/pm-claude-skills --skill readonly-mcp-wrapper -a claude-code`. Or copy the skill folder (skills/readonly-mcp-wrapper in mohitagw15856/pm-claude-skills) into .claude/skills/readonly-mcp-wrapper in your project. Claude Code loads it when a task matches its description.
How do I install Readonly MCP Wrapper in Codex?
Run `npx skills add mohitagw15856/pm-claude-skills --skill readonly-mcp-wrapper -a codex`. Or copy the skill folder (skills/readonly-mcp-wrapper in mohitagw15856/pm-claude-skills) into .agents/skills/readonly-mcp-wrapper in your project. Codex loads it when a task matches its description.
Can I use Readonly MCP Wrapper 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 mohitagw15856/pm-claude-skills --skill readonly-mcp-wrapper -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/readonly-mcp-wrapper, .gemini/skills/readonly-mcp-wrapper, .github/skills/readonly-mcp-wrapper and .opencode/skills/readonly-mcp-wrapper in your project.
What does Readonly MCP Wrapper need to run?
Going by SKILL.md and its folder, Readonly MCP Wrapper needs JavaScript for the scripts in its folder and the command-line tools its instructions call (claude). Our summary lists: Python 3; Node.js.
Does Readonly MCP Wrapper 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 Readonly MCP Wrapper safe to install?
Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
What licence does Readonly MCP Wrapper use?
Readonly MCP Wrapper 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 Readonly MCP Wrapper use?
About 1.3k tokens (SKILL.md is roughly 5.1k 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 1.4k tokens, read only when the agent opens those files.
What are the alternatives to Readonly MCP Wrapper?
Skills that share tags, products or a category with Readonly MCP Wrapper: MCP Server Builder with mcp-use (mcp-use/mcp-use, 11k stars), Documentation Server (andrea9293/mcp-documentation-server, 343 stars), MCP Audit (getsentry/toolkit, 918 stars) and MCP Server Builder (borghei/Claude-Skills, 886 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Readonly MCP Wrapper?
mohitagw15856 (a GitHub user) maintains it in mohitagw15856/pm-claude-skills, which has 1,433 GitHub stars. The repository holds 1,348 skills in this directory. The repository was last updated on October 8, 2026.
Source: mohitagw15856/pm-claude-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.