"deepseek" matching MCP servers:

MCP server for comprehensive PDF processing including text extraction with OCR, keyword search with regex, table extraction, and page preview as Base64 PNG images.

A cheap, fast execution layer for MCP agents that delegates file reads, edits, and command runs to a local DeepSeek Harness, reducing cost and latency while keeping the parent agent in control of planning and reasoning.

Enables peer-to-peer messaging and file exchange between DeepSeek Harness instances via 17 MCP tools, with automatic conversation wake-ups and FRP STCP NAT traversal.

Exposes DeepSeek Harness tools to any MCP-compatible client over streamable HTTP, allowing allowlisted operations such as file read, glob, grep, and web search while preserving the harness's sandbox and approval pipeline.

Enables external MCP clients to drive DeepSeek Harness agents for real coding tasks, providing tools for task execution and queueing, session management, sandboxed file access, preset switching, and usage statistics.

Pluggable local agent capability hub that gives web-based DeepSeek local Agent capabilities (MCP/file operations/skills/desktop automation) and lets local agents reuse the same tools.

Enables DeepSeek Harness to operate files on another computer over MCP, including browsing, reading, writing, editing, searching, moving, and recoverable deletion, with optional command execution. It supports Windows and macOS via LAN or Tailscale with directory authorization and logs.

Enables an agent and a human to work on the same live, editable Word document inside DeepSeek Harness's right Sidebar Browser, where typing and command calls appear immediately in the shared editor session. It also handles panel handoff, editor-session and cursor semantics, Word layout checks, and save/verify rules for DOCX deliverables.

Enables translation of JSON i18n files to multiple languages using various AI providers (Google Gemini, OpenAI, Ollama/DeepSeek) with intelligent caching and deduplication.

Provides weather data via OpenWeatherMap API, file operations, and integration with remote PostgreSQL database for managing accrual records through a FastAPI backend, all accessible through natural language via Deepseek.

Enables users to search XJTLU past exam papers by course code, read details such as academic year, semester, and regular versus resit type, and save the chosen PDFs to local folders after logging in with their own school account. Runs as a local stdio MCP server for Codex and DeepSeek Harness, returning metadata and file paths only.

Adds a local-first memory MCP server: long-term memory is stored as plain Markdown/JSONL files in a user-chosen directory (MEMORY_DIR) and can be shared by multiple MCP clients (Cherry Studio, Claude Desktop, DeepSeek Harness). * No database, no vector store, no network calls * Four tools: memory_read / memory_update / memory_append / memory_search * Shrink-protection + backup before overwrite *