"Files formatted in JSON" matching MCP servers:

Enables Codex to rank available tools and skills, rerank code and documentation search results, and triage saved output artifacts using Jev-based relevance scoring while leaving final decisions to Codex.

Enables searching and retrieving documents from a local folder to ground LLM answers in your files.

Enables natural-language search over locally indexed files such as markdown, text, images, videos, and PDFs, and retrieves indexed text or media metadata by path. It lets Cursor query a local embedding index built with Gemini and SQLite.

MCP server for Scrapiq, providing a tool to extract clean content from URLs. It returns title, content, links, and metadata in text, markdown, or JSON formats.

MCP server for Google's Gemini File Search (RAG). Manage file search stores, upload documents, and query with RAG through 12 tools.

Enables AI assistants to securely connect to Snowflake data warehouses and execute SQL queries through natural language interactions. Supports multiple authentication methods and provides formatted query results with built-in security controls.

A local MCP server that indexes files in a directory using Gemini Embedding 2, enabling AI agents to perform semantic search over local documents.

Context Forge is a vendor-neutral continuity layer for AI tools. It stores project context in Markdown and JSON, retrieves task-scoped context, and leaves structured handoffs so another model can continue without being taught the project again.

A read-only MCP server that provides document awareness for agents by parsing local files into structured profiles, blocks, chunks, and search results, enabling agents to understand and cite document content without dealing with raw file formats.

Provides structured web search capabilities optimized for technical and software development content via providers like OpenRouter. It enables AI agents to perform research and retrieve relevant technical data in a consistent, programmatic JSON format.

Enables running multiple Claude prompts simultaneously in parallel with support for file contexts and output redirection to individual files.

A Model Context Protocol server that transforms text into structured JSON data using templates with placeholders.

This read-only MCP Server allows you to connect to JSON data from Claude Desktop through CData JDBC Drivers. For full CRUD support, check out our MCP Server for JSON (https://www.cdata.com/drivers/json/download/mcp).

Enables agents to optimize context-window attention by reordering retrieved documents so critical evidence lands at prompt boundaries, mitigating lost-in-the-middle degradation. It combines BM25 lexical scoring, dense vector similarity, reciprocal rank fusion, knowledge-graph expansion, and recency-decay memory caching, exposed as a zero-dependency MCP stdio server.

MCP server that allows AI agents to read, search, summarize, and answer questions about local PDF, DOCX, XLSX, and TXT files through five tools.

Enables agents to run hybrid retrieval, reciprocal rank fusion, knowledge graph expansion, semantic caching, and context reordering so critical evidence is placed at prompt boundaries to reduce lost-in-the-middle degradation.

Persistent memory for any AI assistant. Zero token cost until recall. Stores memories in local SQLite, ranks by 6-factor scoring, returns results 79% smaller than JSON. Works with Claude, ChatGPT, Grok, Cursor, Windsurf, and any MCP client.

Enables LibreChat agents to manage per-user private files, persistent documentation, RAG indexing and semantic search, and publish files via secure opaque public links.

Enables storing large command outputs, files, and web pages in a local SQLite index and retrieving only the relevant passages Claude asks for, reducing context usage.

Converts natural language descriptions into validated CanvasXpress JSON configurations for chart generation using RAG and a built-in visualization knowledge base. It supports over 70 chart types and ensures generated configs are compatible with provided data headers and column types.