F
licenseA
qualityD
maintenanceEnables semantic search across multiple AI library documentations to keep coding assistants up-to-date.
1
1
-
byjg-docs-mcp
Officialby byjg
Click on "Deploy 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., "@byjg-docs-mcp search docs for how to map a table to a class"
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.
sidebar_key: mcpserver-byjg-docs tags: [ai, python, docker]
ByJG Docs MCP Server
An MCP server that gives AI assistants semantic search over the documentation of every ByJG open source project -- the same content published at opensource.byjg.com.
Connect your assistant and it can answer questions about the ByJG libraries (MicroOrm, RestServer, Gluo, EasyHAProxy, ...) and cite the documentation page each answer came from.
Related MCP server: Databricks Docs MCP Server
Endpoint
URL |
|
Transport | Streamable HTTP |
Authentication | None -- the documentation is public, so no token is needed |
The URL must end in /mcp.
Most clients accept this shape; the exact file and keys vary per client:
{
"mcpServers": {
"byjg-docs": {
"url": "https://mcpdocs.byjg.com/mcp"
}
}
}Running your own copy? It can require a bearer token instead -- see Authentication.
Add it to your client
Client | Setup | One-click |
Claude Code (CLI) | ||
Claude Desktop | ||
Codex CLI | ||
GitHub Copilot CLI | ||
Gemini CLI | ||
OpenCode | ||
Cursor | ||
VS Code | ||
VS Code Insiders | ||
Visual Studio | ||
JetBrains IDEs | ||
Goose |
| |
LM Studio |
|
The one-click badges hand the endpoint straight to the client, which then asks you to confirm; everything else is the manual configuration on the client page. Connection problems: Troubleshooting.
Neither path installs from a registry. The server is published in the
official MCP Registry as com.byjg/docs, for discovery and provenance: see
The MCP Registry entry.
Tools
Tool | Purpose |
| Ranked passages, each with its public URL |
| Full markdown of one page |
| Inventory of what is indexed |
query accepts natural language ("how do I map a table to a class") or an
exact symbol name (TableAttribute) -- both work. See
the tools in detail.
Privacy
The server records each tool call -- the query, its filters and how well the documentation matched -- to find what the docs do not cover yet. The log stays on the server and is not shared. Do not put secrets in a query.
Development
To run the server yourself, self-host it, or change the code, see Development.
Available Tools
3 toolsget_documentRead a documentation pageAInspect
Return the full markdown of one documentation page, addressed by the source path reported in a search result (for example php/micro-orm/active-record.md). Use it when a search hit is relevant but truncated and you need the whole page.
Inputs: source_path (required). Returns: result
list_projectsList documented projectsAInspect
Inventory of everything indexed, grouped by category and project, with document and passage counts. Use it to discover which ByJG libraries have documentation before searching.
Inputs: no named parameters. Returns: result
search_docsSearch ByJG documentationAInspect
Search the ByJG open source documentation and return the most relevant passages, each with its public URL. Combines semantic and keyword matching, so both natural-language questions ('how do I map a table to a class') and exact symbol names ('TableAttribute') work. Optionally narrow to a category (php, devops, js, ai, helm) or a project (micro-orm, restserver, docker-easy-haproxy, ...).
Inputs: query (required), limit, project, category. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
A4.4/5.0
Scored across 3 tools
Disambiguation5/5
Each tool has a clearly distinct role: search_docs finds relevant passages, get_document retrieves a full page, and list_projects provides an inventory. There is no functional overlap or ambiguity between them.
Naming Consistency5/5
All tool names follow a consistent verb_noun snake_case pattern: search_docs, get_document, list_projects. The naming is predictable and easy for an agent to infer.
Tool Count5/5
Three tools is well-scoped for a documentation MCP server: discover, search, and retrieve. Each tool earns its place with no redundancy or unnecessary surface area.
Completeness5/5
The tool set covers the full documentation workflow: list_projects provides the inventory, search_docs finds relevant content, and get_document retrieves full pages. There are no obvious missing operations for the stated purpose.
Maintenance
ActivityActive
ResponsivenessNo recent community issues
Related MCP Connectors
Versioned documentation registry and semantic search for AI tools and coding assistants.
Search and read Vector Panda docs: API operations, pricing, storage tiers, measured benchmarks.
Ingest, manage, and retrieve documents for RAG-powered AI applications
Token-efficient search for coding agents over public and private documentation.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables semantic search over Databricks docs, API reference, Terraform provider docs, and knowledge base via tools like search_databricks_docs and research.-
- FlicenseBqualityDmaintenanceEnables AI assistants to query and search library documentation from GitHub repositories or web pages using RAG and web scraping.2-
- AlicenseNot gradedqualityDmaintenanceEnables LLMs to search and retrieve information from large technical documentation (OpenAPI specs, markdown) via intelligent chunking and semantic search.MIT