MCP Specification Server
Supports Claude Desktop installation on macOS with specific configuration path at ~/Library/Application Support/Claude/claude_desktop_config.json
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MCP Specification Serverexplain the Tools section of the MCP specification"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP Specification Server
Overview
We turned the Model Context Protocol documentation into an MCP server so that your LLM can get context on the full MCP specs. Query specific sections like "Tools", "Resources", "Authorization", and 20+ others to get the complete documentation for that section.
Features
📚 Complete MCP Specification Access
364KB of comprehensive MCP documentation indexed and searchable
25+ distinct sections covering every aspect of the protocol
Complete section content returned, not just snippets
⚡ Smart Document Processing
Intelligent chunking by major headings (
#tags)500-line chunk limits for optimal performance
Fast startup indexing (<1 second)
🔧 Developer-Focused Sections
Tools - Function calling and tool execution patterns
Resources - Data access and resource management
Authorization - Security, authentication, and authorization
Transports - Communication layers (stdio, HTTP, SSE)
Debugging - Troubleshooting and development tools
Core components - Protocol architecture fundamentals
Connection lifecycle - Initialization and termination
And 18+ more specialized sections
🛠️ Built for MCP Development
Perfect for developers building MCP servers or clients
Reference implementation patterns and best practices
Complete protocol specifications at your fingertips
Related MCP server: Swagger/OpenAPI MCP Server
Install with an IDE
Add this server to any MCP-compatible client (Claude Desktop, Cursor, VSCode, Windsurf, etc.):
Claude Desktop Config:
macOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows:
%APPDATA%\Claude\claude_desktop_config.json
Cursor config:
Chat Settings, Tools / Integrations. Edit mcp.json
{
"mcpServers": {
"mcp-spec": {
"command": "npx",
"args": ["-y", "@mcpjam/mcp-spec@latest"]
}
}
}How it works
┌─────────────────┐ ┌──────────────────┐ ┌─────────────────┐
│ MCP Client │◄──►│ MCP Spec Server │◄──►│ Specification │
│ (Claude, │ │ │ │ Document │
│ Your App) │ │ - Section Index │ │ (llms-full.md) │
└─────────────────┘ │ - Content Cache │ └─────────────────┘
│ - Search Logic │
└──────────────────┘Server indexes the complete MCP specification on startup
Document is split into sections by major headings
Query by section name to get the full content for that section
Returns complete documentation for topics like Tools, Resources, Authorization, etc.
Contributing
Want to improve this server? Here's how:
# 1. Clone the repository
git clone https://github.com/your-org/mcp-spec.git
cd mcp-spec
# 2. Install dependencies
npm install
# 3. Build the project
npm run build
# 4. Start development server
npm run devDevelopment workflow:
Fork this repository
Create a feature branch:
git checkout -b my-featureMake your changes
Test locally:
npm run build && npm run devSubmit a pull request
Community: Join the MCP community discussions
Note: This is an unofficial server created to make the MCP specification more accessible. For official MCP resources and documentation, visit modelcontextprotocol.io.
Available Tools
1 toolmcpjam_search_mcp_specC
Search the MCP specification document for relevant content
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Select a specific section of the MCP specification to retrieve. |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
There are no annotations, and the description provides no behavioral information such as what the tool returns (e.g., text, citations), side effects, or error scenarios. For a search tool, this is a significant omission; the agent knows it searches but not what the output looks like.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is one sentence of eight words, which is concise but perhaps too minimal. It could benefit from a bit more detail without becoming verbose. It is front-loaded but overly sparse.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the absence of an output schema and annotations, the description should compensate by explaining what the tool returns. It does not. The schema's enum helps, but the description does not clarify that the output is the content of the selected section. The tool feels incomplete for an agent to use confidently.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage with a clear description for the parameter. The tool description adds no additional semantic value beyond what the schema already provides, so the baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it searches the MCP specification document, but does not explicitly indicate that the search is restricted to the predefined sections listed in the enum. The combination of the description and the schema's enum makes the purpose clear, but the description alone could be slightly more precise.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No usage guidelines are provided. Since there are no sibling tools, the guidance is not strictly needed, but the description does not mention when to use this tool or any limitations. The agent can infer usage from the context, but the lack of explicit guidance is a slight gap.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
1 tool update
- First observed
mcpjam_search_mcp_spec
TDQS
With only one tool, there is no possibility of confusion between tools, so disambiguation is perfect.
The single tool name follows a clear pattern (prefix_verb_noun) and is internally consistent.
One tool is borderline thin for a server; while it may be sufficient for a simple search utility, typical specification servers offer more operations.
The server only provides search, missing obvious operations like retrieving specific sections or listing contents, making the toolset incomplete for comprehensive specification interaction.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
The Mercado Pago MCP Server implements the Model Context Protocol to provide AI agents and LLMs with access to Mercado Pago's APIs and tools within compatible development environments. It acts as an intermediary that translates Mercado Pago resources into executable functions (tools) that AI applications can invoke to perform actions and automate flows. The server simplifies integration, enables using documentation to implement or improve code, and optimizes operations through natural language interactions without manual implementations.
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Augments MCP Server - A comprehensive framework documentation provider for Claude Code
MCP server for agentverse documentation, generated by doc2mcp.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceA customized MCP server that enables integration between LLM applications and documentation sources, providing AI-assisted access to LangGraph and Model Context Protocol documentation.-
- AlicenseDqualityDmaintenanceA Model Context Protocol server that enables LLMs to explore and interact with API specifications by providing tools for loading, browsing, and getting detailed information about API endpoints.41614ISC
- AlicenseAqualityBmaintenanceAn MCP (Model Context Protocol) server that provides structured access to ISO 32000 (PDF) specification documents. Enables LLMs to navigate, search, and analyze PDF specifications through well-defined tools.83862MIT
- AlicenseNot gradedqualityFmaintenanceProvides comprehensive access to the Model Context Protocol specification through prompts and resources, enabling evaluation of server compliance and detailed explanations of MCP topics.2425MIT
Appeared in Searches
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/MCPJam/mcp-spec'
If you have feedback or need assistance with the MCP directory API, please join our Discord server