Los mejores MCP servers de Docs & Knowledge para Codex

Provides a local knowledge graph that connects source code, documentation, and infrastructure to give AI agents structural context.

[mcp_servers.codebase-memory-mcp]
command = "npx"
args = ["-y", "codebase-memory-mcp"]

Lets an AI client read, write, and search a local-first knowledge graph stored as Markdown files.

[mcp_servers.basic-memory]
command = "uvx"
args = ["basic-memory"]

Fetches up-to-date, version-specific library documentation and code examples into an AI coding agent's context.

[mcp_servers.context7]
command = "npx"
args = ["-y", "@upstash/context7-mcp"]

Lets AI clients search the web, fetch full page content as markdown, and run multi-step research agents.

[mcp_servers.exa-mcp-server]
url = "https://mcp.exa.ai/mcp"

Lets an AI client search, scrape, crawl, map, and interact with web pages as clean Markdown or structured data.

[mcp_servers.firecrawl-mcp-server]
command = "npx"
args = ["-y", "firecrawl-mcp"]

Gives AI clients semantic search over official Microsoft docs, page fetching as markdown, and Azure code sample lookup.

[mcp_servers.mcp]
url = "https://learn.microsoft.com/api/mcp"

Lets an AI client search, inspect, lint, and install Agent Skills (SKILL.md) from the SkillMD registry.

[mcp_servers.skillmd]
command = "npx"
args = ["-y", "get-skill"]

Allows AI clients to explore the Claude Code source code by browsing tools, commands, and searching the codebase.

[mcp_servers.codemaster]
command = "npx"
args = ["-y", "@divyesh2000/codemaster"]

Lets AI agents read, redline, and apply native Word Track Changes to DOCX files without breaking formatting.

[mcp_servers.adeu]
command = "npx"
args = ["-y", "@adeu/mcp-server"]

Validates oh-my-posh configuration files and segment snippets against the official schema, returning errors and warnings.

[mcp_servers.validator]
url = "https://ohmyposh.dev/api/mcp"

Generates architecture diagrams, explanations, Mermaid source, and narrated videos for GitHub repositories.

[mcp_servers.gitdiagram]
url = "https://gitdiagram.com/mcp"

Lets AI coding agents query a prebuilt index of a codebase's graph, git history, tests and decisions instead of grepping files.

[mcp_servers.repowise]
command = "uvx"
args = ["repowise"]

Compiles raw documents into a cited, interlinked markdown wiki that agents can query, review, and use as a stable knowledge base.

[mcp_servers.llm-wiki-compiler]
command = "npx"
args = ["-y", "llm-wiki-compiler"]

Lets AI clients run private web searches, read URLs, and get query suggestions through a SearXNG instance.

[mcp_servers.mcp-searxng]
command = "npx"
args = ["-y", "mcp-searxng"]

Provides an AI client with a searchable, cited knowledge base of CPU performance engineering literature, benchmarks, and technical documentation.

[mcp_servers.cpu-perf]
command = "uvx"
args = ["cpu-perf"]

Search StyleKit design styles and fetch tokens, recipes, assets, and lint checks for AI-generated UI code.

[mcp_servers.stylekit-mcp]
command = "npx"
args = ["-y", "stylekit-mcp"]

Lets an AI client review flashcards, create and edit notes, manage decks, tags, media, and note types in Anki via AnkiConnect.

[mcp_servers.anki-mcp-server]
command = "npx"
args = ["-y", "@ankimcp/anki-mcp-server"]

Scans web pages, Office, PDF, ePub and Markdown files for WCAG accessibility issues and reports violations.

[mcp_servers.accessibility-agents]
command = "npx"
args = ["-y", "@community-access/accessibility-agents-mcp"]