DeepSeekSAFE
Model Context Protocol server for DeepSeek's advanced language models
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
An MCP server for DeepSeek's current V4.1 Flash API: text and visual chat, the Responses API, FIM completion, Files API lifecycle operations, model discovery, balance checks, and bounded in-memory conversations.
Version 1.0.1 uses the stable MCP TypeScript SDK v2 and serves both the 2026-07-28 protocol and stateless legacy clients.
What's current
As of September 10, 2026:
- The canonical fast model is
deepseek-flash, currently DeepSeek V4.1 Flash. deepseek-v4-flashanddeepseek-v4-flash-vision-expare temporary aliases
for deepseek-flash.
- DeepSeek announced that
deepseek-v4-prowill begin serving V4.1
1b524d3a28beOBSERVED · 2026-10-02Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add deepseek-mcp-server --env DEEPSEEK_API_KEY=${DEEPSEEK_API_KEY} --env DEEPSEEK_API_KEY=${DEEPSEEK_API_KEY} -- npx -y [email protected]claude mcp add deepseek-mcp-server:0.5.0 --env DEEPSEEK_API_KEY=${DEEPSEEK_API_KEY} --env DEEPSEEK_API_KEY=${DEEPSEEK_API_KEY} -- docker run -i --rm docker.io/dmontgomery40/deepseek-mcp-server:0.5.0:NoneExposed tools (11)
7 read · 2 write · 2 destructive. Blast radius: 2 tools can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
chat_completion | read | |
completion | read | |
create_response | write | |
delete_file | destructive | |
get_user_balance | read | |
list_conversations | read | |
list_files | read | |
list_models | read | |
reset_conversation | destructive | |
retrieve_file | read | |
upload_file | write |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (7)
delete_file, reset_conversation
The endpoint defaults to `http://127.0.0.1:3001/mcp`.
new URL(`http://127.0.0.1:${address.port}/mcp`),const preflight = await fetch(`http://127.0.0.1:${address.port}/mcp`, {const rejectedOrigin = await fetch(`http://127.0.0.1:${address.port}/mcp`, {new URL(`http://127.0.0.1:${address.port}/mcp`),@modelcontextprotocol/node, @modelcontextprotocol/server, dotenv, hono, zod, @modelcontextprotocol/client, @types/node, typescript
Gates applied: no_behavioural_pass.
1b524d3a28befull audit observations/trust-audit/mcp-server/dmontgomery40__deepseek-2.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-02 | 1b524d3a28be | SAFE | B | 89 | first audit |
Questions
What is the DeepSeek MCP server?
Model Context Protocol server for DeepSeek's advanced language models
What tools does DeepSeek expose?
11 in total: 7 read-only, 2 that write, and 2 that can delete or overwrite (delete_file, reset_conversation). Every one is listed on this page with its risk.
Is DeepSeek safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B. Separately from the audit: 2 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does DeepSeek need?
It reads DEEPSEEK_API_KEY and DEEPSEEK_MCP_AUTH_TOKEN from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does DeepSeek run?
It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on npm as deepseek-mcp-server at 1.0.1.
How current is this page?
The grade is for one exact copy of the source (1b524d3a28be), read on 2026-10-02. The repository is watched and re-audited when it changes.