Skip to main content
Glama

deepseek-tools-mcp

CI

Unofficial MCP server that exposes DeepSeek's standalone tools APIs as MCP tools: Web Search, Fetch, OCR, ASR and TTS.

非官方项目,与 DeepSeek 无隶属关系。DeepSeek 及其 API 的条款与定价以官方文档为准。 This project is not affiliated with DeepSeek. Use it under DeepSeek's own terms and pricing.


Why this exists

DeepSeek opened its standalone tools API in 2026 and added OCR / ASR / TTS shortly after. Those are plain REST endpoints, which makes them a natural fit for MCP — but most existing MCP wrappers only cover Search and Fetch, and the in-conversation server tools (deepseek_web_search, deepseek_read_url) cannot be reused outside a model round-trip.

This server wraps the standalone APIs so any MCP client can call them directly:

MCP tool

DeepSeek endpoint

Notes

deepseek_search

POST /v1/tools/search

Query operators, count 1–50, ori_question hint

deepseek_fetch

POST /v1/tools/fetch

Page to Markdown, offset paging for long pages

deepseek_ocr

POST /v1/tools/ocr

PDF / Word / PowerPoint / images, per-page text

deepseek_asr

POST /v1/tools/asr

WAV (16-bit PCM) or Ogg Opus, ≤8 MiB / ≤120 s

deepseek_tts

POST /v1/tools/tts

wav / pcm, written to a local file

It deliberately does not wrap deepseek_web_search or deepseek_read_url: those are server-side tools that require a model round-trip, and the standalone Search/Fetch APIs cover the same ground more cheaply.

Related MCP server: mcp-deepseek-search

Requirements

  • Node.js >= 20

  • A DeepSeek API key with access to the tools API

Quick start

DEEPSEEK_API_KEY=sk-... npx -y deepseek-tools-mcp

From source:

git clone https://github.com/wuzhechen/deepseek-tools-mcp.git
cd deepseek-tools-mcp
npm install
npm run build
DEEPSEEK_API_KEY=sk-... node dist/src/index.js

The server speaks MCP over stdio; stdout is the protocol channel, logs go to stderr.

Client configuration

Claude Code

claude mcp add deepseek-tools \
  --env DEEPSEEK_API_KEY=sk-... \
  -- npx -y deepseek-tools-mcp

CC Switch (and dsh)

Add a new stdio MCP server:

{
  "type": "stdio",
  "command": "npx",
  "args": ["-y", "deepseek-tools-mcp"],
  "env": { "DEEPSEEK_API_KEY": "sk-..." }
}

CC Switch writes MCP entries into each app it manages — for DeepSeek Harness that means ~/.dsh/profiles/<profile>/cordis.patch.yml as a @deepseek-ai/dsh-mcp-client entry, so the same tools become available to Claude Code and dsh.

Generic MCP config

See examples/mcp.json.

Environment variables

Variable

Default

Description

DEEPSEEK_API_KEY

— (required)

DeepSeek API key. Read from the server process environment only.

DEEPSEEK_TOOLS_BASE_URL

https://api.deepseek.com/v1/tools

Override for proxies or private deployments.

DEEPSEEK_TOOLS_MAX_OUTPUT_CHARS

20000

Cap on characters returned per call (search / fetch / ocr). Minimum 1000.

DEEPSEEK_TOOLS_ALLOWED_DIRS

unset (any path)

Optional :-separated allowlist for local file reads (OCR / ASR).

Tool reference

Input

Type

Description

query

string, 1–128 chars

Supports site: / -site:, -term, "exact phrase", lang:, after:, before:.

count

int, 1–50, default 10

Number of results.

ori_question

string, ≤128 chars

Original user question, improves recall.

need_content

boolean, default false

Ask for page content too (heavier).

localization

string

Optional locale/IP hint.

Returns numbered results with title, URL, summary/snippet, date and authority.

deepseek_fetch

Input

Type

Description

url

string

http/https only, ≤8192 chars.

offset

int, default 0

Character offset for paging.

max_chars

int, 1000–50000, default 20000

Chunk size per call.

Returns URL, the character range and the Markdown content. When the page is longer, the header includes the next offset.

deepseek_ocr

Input

Type

Description

file_path

string

PDF, doc/docx, ppt/pptx, png/jpeg/webp/gif/bmp/tiff. Max 100 MiB, 1000 pages.

purpose

text_recognition (default) or rich_layout_recognition

text_recognition extracts text directly from text-only Office files; rich_layout_recognition OCRs every page.

Returns page-count and --- page N --- blocks. The API budget is 180 s end-to-end; this tool waits up to 200 s.

deepseek_asr

Input

Type

Description

file_path

string

16-bit PCM WAV or Ogg Opus. Max 8 MiB and 120 s. Stereo uses the left channel.

Returns text and duration_ms.

deepseek_tts

Input

Type

Description

text

string

Non-empty. Up to 10000 billed characters (Chinese counts as 2) and a 64 KiB request body.

voice_id

stella (default) / tide

Female / male voice.

format

wav (default) / pcm

pcm is raw 24 kHz, 16-bit, mono.

filter_markdown

boolean, default true

Strip Markdown before synthesis.

output_path

string

Optional. Defaults to ~/.cache/deepseek-tools-mcp/tts-<timestamp>.<format>.

Audio is written to a file and the tool returns the path, format, content type and byte size.

Limits and pricing

Limits below are enforced by the API; see the official docs for the current values.

  • Search / Fetch: per-request pricing (about ¥5 per 1000 successful calls), rate limited per account.

  • OCR: max 100 MiB, 1000 pages, 180 s total; about ¥1.5 per 1000 pages.

  • ASR: max 8 MiB, 120 s; priced per audio hour.

  • TTS: max 10000 billed chars and 64 KiB body; priced per character.

Only successful requests are billed. Verify prices and quotas in the official guide before relying on them.

Security notes

  • The API key is read from the environment and never logged or written to disk.

  • OCR/ASR read only the file path you pass; set DEEPSEEK_TOOLS_ALLOWED_DIRS to confine reads.

  • TTS writes only to output_path (or the cache directory) and creates the parent directory.

  • No shell execution, no network access beyond the configured DEEPSEEK_TOOLS_BASE_URL.

  • Responses are capped by DEEPSEEK_TOOLS_MAX_OUTPUT_CHARS to protect the model's context.

Development

npm install
npm run build
npm test                 # unit tests (mocked fetch)
npm run smoke            # live API calls; requires DEEPSEEK_API_KEY

Live OCR / ASR checks:

SMOKE_OCR_FILE=/path/to/file.pdf \
SMOKE_ASR_FILE=/path/to/audio.wav \
DEEPSEEK_API_KEY=sk-... npm run smoke

License

MIT

Available Tools

5 tools
deepseek_asrDeepSeek ASRA

Transcribe a local WAV (16-bit PCM) or Ogg Opus audio file with DeepSeek's ASR API. Max 8 MiB / 120 seconds.

Inputs: file_path (required).

deepseek_fetchDeepSeek FetchA

Fetch a web page through DeepSeek's Fetch API and return its readable content as Markdown. Supports character-offset paging for long pages.

Inputs: url (required), offset, max_chars.

deepseek_ocrDeepSeek OCRA

Extract text from a local PDF, Word, PowerPoint or image file with DeepSeek's OCR API. Returns per-page text.

Inputs: file_path (required), purpose.

deepseek_ttsDeepSeek TTSA

Synthesize speech with DeepSeek's TTS API and write the audio to a local file. Returns the saved path, format and byte size.

Inputs: text (required), format, voice_id, output_path, +1 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.9/5.0

    Scored across 5 tools

    Disambiguation5/5

    Each tool maps to a clearly distinct capability: web search, page fetch, OCR, ASR, and TTS. There is no meaningful overlap between their purposes, so an agent can select the right tool from the task type alone.

    Naming Consistency5/5

    All tools use a consistent deepseek_ prefix followed by a concise snake_case action or modality name. The pattern is predictable and easy to scan.

    Tool Count5/5

    Five tools is well-scoped for a multimodal API wrapper covering search, retrieval, and audio/document processing. Each tool earns its place without redundancy.

    Completeness4/5

    The surface covers the core modalities promised by the server: search, fetch, OCR, ASR, and TTS. Minor gaps exist, such as no URL-based OCR/ASR or batch processing, but these are workaroundable and not central to the stated purpose.

    Maintenance

    ActivityMaintained
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      C
      maintenance
      Exposes DeepSeek's Search and Fetch REST APIs as two read-only MCP tools, letting any MCP-capable agent run ranked web searches and retrieve individual pages as truncated Markdown. Works with whichever model the host runs, over stdio or Streamable HTTP.
      2
      MIT
    • A
      license
      A
      quality
      C
      maintenance
      Exposes DeepSeek's web search and page-fetch tools to any MCP client, letting any LLM run searches with quality signals like rerank score and source authority, plus advanced query syntax. It also retrieves single pages as Markdown, with built-in throttling, retries, and size-conscious summaries.
      2
      101 npm
      2
      MIT
    • A
      license
      A
      quality
      C
      maintenance
      Enables web search and page fetching through the DeepSeek Search and Fetch APIs, exposing search and fetch tools to MCP clients. Supports paginated content retrieval with cursors so long pages can be read in chunks without repeating upstream requests.
      2
      32 npm
      AGPL 3.0
    • A
      license
      A
      quality
      C
      maintenance
      Enables MCP clients to run web searches that return ranked results with titles, URLs, snippets, summaries, and optional extracted page content, and to fetch HTTP or HTTPS pages as Markdown. It runs over stdio as a zero-dependency Python server that uses DeepSeek's official APIs and any supported MCP client.
      2
      2
      MIT