A
licenseNot graded
qualityB
maintenanceEnables semantic search over local Markdown documentation using hybrid retrieval combining embeddings, keyword search, and graph traversal with automatic file watching and zero-configuration setup.
2
MIT
Inkdex
by antonlunden
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., "@Inkdexsearch docs for refresh token expiration"
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.
Inkdex
MCP server for semantic search over markdown docs.
Tools
Tool | Description |
| Search indexed documentation. Returns matching chunks ranked by relevance. |
Related MCP server: QMD - Query Markdown
Usage
Add to your MCP client configuration:
{
"mcpServers": {
"inkdex": {
"command": "npx",
"args": [
"-y",
"inkdex"
],
"env": {
"DOCS_PATH": "/path/to/your/docs"
}
}
}
}Variable | Required | Description |
| Yes | Path to the directory containing markdown files to index |
How it works
Markdown files are split into chunks by heading structure and paragraph boundaries. Chunks are embedded locally using all-MiniLM-L6-v2 and stored in SQLite.
Search ranks results using both vector similarity and BM25 full-text matching, combined via Reciprocal Rank Fusion.
Results include the source, context, and text:
[mira/authentication.md]
<context>
Authentication > Token Expiration and Refresh
</context>
The refresh token expires...Available Tools
1 toolsearch_docsA
Search documentation for relevant information. Returns content that matches the query semantically.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Search query - natural language question or keywords |
TDQS
A3.5/5.0
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It does disclose that matching is semantic rather than keyword-based, which is a useful behavioral trait. However, it doesn't explain what the returned 'content' looks like, any limits, or authentication requirements, leaving some gaps.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is just two short sentences with no redundant information. It front-loads the core purpose and adds a meaningful behavioral detail about semantic matching. Every sentence earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is simple with one fully documented parameter, but there is no output schema or annotations. The description clarifies the purpose and semantic matching but doesn't describe the return format or scope of results. This is a minor gap, making it adequate but not complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema fully describes the 'query' parameter as a natural language question or keywords (100% coverage). The description adds no parameter-specific information, so the schema already provides the necessary meaning. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's function: searching documentation and returning semantically relevant content. The verb 'search' and resource 'documentation' are specific, and since there are no sibling tools, differentiation is not an issue. However, 'documentation' is somewhat broad, so it doesn't earn a perfect 5.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies the tool is for finding information in documentation, but it provides no explicit guidance on when to use it or when not to. There are no sibling tools to contrast with, so the lack of alternatives is understandable, but the description still doesn't offer any usage context beyond the basic purpose.
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
v0.4.0- First observed
search_docs
TDQS
A3.6/5.0
Disambiguation5/5
Only one tool exists, so there is no possibility of confusion between tools. Its purpose is clear.
Naming Consistency5/5
The single tool name 'search_docs' uses a clear verb_noun structure in snake_case, consistent with common naming conventions.
Tool Count3/5
A single tool is borderline; it may be sufficient for a narrow search-only purpose but feels thin for a broader documentation server.
Completeness3/5
The tool covers semantic search but lacks other potentially useful operations like retrieving a specific document or listing available documentation, which are common in documentation servers.
Maintenance
ActivityInactive
ResponsivenessSyncing
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
Search and reason over your Obsidian-style Markdown vault, right from ChatGPT.
Versioned documentation registry and semantic search for AI tools and coding assistants.
Ingest, manage, and retrieve documents for RAG-powered AI applications
Serve a folder of Markdown notes as an MCP server: hybrid search, reading, and sourced answers.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceProvides hybrid search over local markdown knowledge bases using BM25 keyword search and vector semantic search. Enables indexing, querying, and retrieving markdown documentation with dual-mode support for local and remote agents.46,33216MIT
- AlicenseNot gradedqualityCmaintenanceSemantic search over any markdown corpus using local embeddings. Provides tools to search, reindex, and get index stats, with results including file paths, line numbers, and header breadcrumbs.MIT
- AlicenseNot gradedqualityDmaintenanceProvides local semantic search over files using embeddings, enabling directory indexing and natural language queries without external services.MIT
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/antonlunden/inkdex'
If you have feedback or need assistance with the MCP directory API, please join our Discord server