deepseek-mcp
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., "@deepseek-mcp Review my uncommitted changes for bugs"
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.
deepseek-mcp
A local MCP server that makes DeepSeek available to your primary coding agent for code review and second opinions.
The server reads the repo itself. Your agent passes a git ref or a list of paths — never the code — so a review costs about twenty tokens on the way in instead of several thousand.
Tools
Tool | Use it for | Model |
| Review a diff. Uncommitted work by default, or a branch via | review |
| Review whole files — architecture, an unfamiliar module, a suspected bug. | review |
| Ask a specific question. Supports multi-turn via | consult |
All three are read-only and take paths, not content.
Related MCP server: ProjectBrain
Install
npm i -g @berrydev-ai/deepseek-mcpThat puts a deepseek-mcp binary on your PATH; no checkout needed. Or skip
the install and let your MCP client fetch it on demand with
npx -y @berrydev-ai/deepseek-mcp, at the cost of a slower cold start.
One caveat if you install from source instead: avoid
npm i -g git+https://github.com/berrydev-ai/deepseek-mcp.git. On npm 10.x
it appears to succeed but symlinks the global package at a bare clone in the
cache with no working tree, leaving bin dangling. Use the registry, or a
tarball. dist/ is committed so that installing from git or a tarball still
works — a global install has no devDependencies, so nothing can compile at
install time.
Configure
There is no dotenv loader. The server reads process.env and nothing else,
so .env is a reference for what to set rather than a file that gets read.
Configuration belongs in your MCP client's env block.
Claude Code
claude mcp add deepseek -s user -e DEEPSEEK_API_KEY=sk-... -- deepseek-mcp-s user registers it across all your projects. Without it the default is
local scope, which is limited to the directory you ran the command in.
Codex
codex mcp add deepseek --env DEEPSEEK_API_KEY=sk-... -- deepseek-mcpNote --env rather than Claude's -e, and that the command to launch goes
after -- in both. Codex writes to ~/.codex/config.toml globally, so there
is no scope flag to think about. The equivalent by hand:
[mcp_servers.deepseek]
command = "deepseek-mcp"
[mcp_servers.deepseek.env]
DEEPSEEK_API_KEY = "sk-..."Verify with codex mcp get deepseek, and codex mcp remove deepseek to undo.
Any other MCP client
{
"mcpServers": {
"deepseek": {
"command": "deepseek-mcp",
"env": {
"DEEPSEEK_API_KEY": "sk-..."
}
}
}
}Note that a missing key does not stop the server from starting, so the client
will report it as connected either way — assertConfigured only fires on the
first tool call. If every call comes back with "DEEPSEEK_API_KEY is not set",
the env block is the place to look.
The server operates on its working directory, which is normally your project.
Set DEEPSEEK_REPO_ROOT to override.
Local development
git clone https://github.com/berrydev-ai/deepseek-mcp.git
cd deepseek-mcp && npm install && npm run buildRun npm run build and commit dist/ alongside any source change, otherwise
installs keep serving the previous build.
Direct or through AI Gateway
One env var, no code change. https://api.deepseek.com is the default and has
no dependencies. Pointing DEEPSEEK_BASE_URL at a Cloudflare AI Gateway
endpoint instead gets you request logs, spend caps, caching and the ability to
swap models without touching this repo — worth it the moment you want to
compare two models on the same review.
Tuning the prompts
prompts/review.md and prompts/consult.md are the entire behaviour of the
server. They are plain markdown; edit and restart. Both are written to keep
output tight, because whatever DeepSeek returns lands in your primary agent's
context window and competes with everything else there.
The review prompt enforces severity grouping and file:line anchors, and
forbids restating what the code does. If reviews come back vague, the fix is
almost always in that file rather than in the TypeScript.
Getting it actually invoked
The most common failure mode is not a bug — it is that the primary agent never
calls the tool. Coding agents are reluctant to delegate. The tool descriptions
are written to draw a clear line (substantial changes yes, one-line edits no),
but you may still need to ask for it explicitly at first, or add a line to your
CLAUDE.md telling the agent to get a DeepSeek review before opening a PR.
Delegation only pays for itself on work that involves reading and analysing real amounts of code. On small tasks the per-call overhead dominates.
Guards
Paths are resolved and rejected if they escape the repo root.
Git refs are validated so an argument cannot be smuggled in as an option.
Input is truncated at a character budget, and the response says when that happened.
Model calls abort at 55s, below the ~60s tool-call timeout most clients enforce, so you get a clear message rather than a hang.
Every response carries a footer with file count, model and token usage.
Notes
Built on @modelcontextprotocol/server v2 via serveStdio, which serves both
the 2025 and 2026-07-28 protocol revisions from one factory — clients on either
revision work without configuration.
Model defaults are deepseek-v4-flash for reviews and deepseek-v4-pro for
consults. Check them against whichever endpoint you point at — the names move
over time.
Watch out for the older deepseek-chat and deepseek-reasoner names. They
still return 200, but the response comes back as deepseek-v4-flash, so a
stale value costs you the reasoning model without ever raising an error. The
model in the response footer is read from the provider's reply rather than
from your config, so it will tell you what actually ran.
License
MIT — see LICENSE.
Available Tools
3 toolsconsultConsult DeepSeekARead-only
Ask DeepSeek a specific engineering question as a second opinion — design trade-offs, a decision you are unsure about, or a bug you cannot place. Attach files by path rather than pasting them. For multi-turn exchanges, pass the prior turns in history so the answer builds on them.
Inputs: question (required), paths, context, history.
review_changesReview changes with DeepSeekARead-only
Get an independent code review from DeepSeek on the current git changes. The server runs the diff itself, so do NOT paste code into this call — just say which changes to look at. Worth using for substantial changes (a feature, a refactor, anything before a PR); not worth the round trip for one-line edits. Returns findings grouped by severity with file:line anchors.
Inputs: base, focus, paths.
review_filesReview whole files with DeepSeekARead-only
Get a DeepSeek review of complete files rather than a diff. Use when the question is about existing code rather than a change — architecture, a suspected bug, or an unfamiliar module. Pass paths only; the server reads them.
Inputs: paths (required), focus.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
Each tool has a clearly distinct purpose: review_changes focuses on git diffs, review_files on complete files, and consult on general engineering questions. There is no overlap or ambiguity in what each tool does.
Two tools follow a consistent verb_noun pattern (review_changes, review_files), while consult is a single verb but still clear and in line with the action-oriented naming. Minor deviation from the review_ prefix but not chaotic.
Three tools is a well-scoped set for the server's purpose of providing DeepSeek-powered code assistance. Each tool covers a distinct need without unnecessary redundancy.
The tool surface covers the full range of use cases for the domain: reviewing changes, reviewing existing files, and asking general engineering questions. No obvious gaps exist for an AI consultation server.
Maintenance
Related MCP Connectors
Shared memory MCP server for Claude Code, Codex, Gemini CLI and Cursor. Cited, editable.
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
Repository knowledge graph MCP server for codebase understanding and debugging.
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
Related MCP Servers
- AlicenseCqualityCmaintenanceA privacy-first MCP server that provides local LLM-enhanced tools for code analysis, security scanning, and automated task execution using backends like Ollama and LM Studio. It enables symbol-aware code reviews and workspace exploration while ensuring that all code and analysis remain strictly on your local machine.36ISC
- AlicenseBqualityDmaintenanceLocal MCP server providing project cognition capabilities for AI coding agents, including context packs, impact analysis, and git diff review through stdio communication.103MIT
- AlicenseNot gradedqualityDmaintenanceMCP server for automated code review using AI agents. It analyzes code diffs or file paths for bugs, security issues, and style violations.MIT
- AlicenseNot gradedqualityBmaintenanceA self-hosted MCP server that enables AI coding agents to read, edit, search, and run code in local projects with human review loops and policy controls.MIT