deepseek-mcp-bridge (CassiaTw1g/deepseek-mcp-bridge) is an MCP server listed on the M8ven Trust Index. It scores 74 out of 100, grade C. It declares 2 tools. No publisher has claimed this listing.

Back to MCP Trust IndexM8ven
C
Emerging
74/100

deepseek-mcp-bridge

MCP server that exposes DeepSeek as a tool for ChatGPT connectors

→ CassiaTw1g/deepseek-mcp-bridge· listed on github_repo_search

Emerging. No concerning findings. Grades remain capped until the project builds reputation through adoption. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

Code Verified⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every pushwhy connect →

Who stands behind it

CassiaTw1g

Source: github_repo_search

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

⚡ Connect GitHub for Live Monitored

Install from

GitHub

The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.

// key findings
🚨
Secret credentials may flow to a network call
1 flow detected: DEEPSEEK_API_KEY. We can’t prove the destination matches the brand the credential belongs to.
🔐
You'll be asked for 2 credentials: DEEPSEEK_API_KEY, MCP_PATH_SECRET
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// environment variables
To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.
configBRIDGE_ANTHROPIC_BASE_URLWhere the harness sends its requests.
configBRIDGE_APPROVAL_TIMEOUT_MSHow long a command waits for a human (5 min). Expiry is a deny.
configBRIDGE_APPROVE_ALLOWComma-separated pre-approved command names. Anything else pauses the job for a human.
configBRIDGE_CC_APPROVALSet to off to skip the approval queue entirely — every command then runs unattended. Only for npm run accept.
configBRIDGE_CC_MAX_BUDGET_USDOpt-in --max-budget-usd for the harness. Left off by default because Claude Code prices at Claude rates — a limit set here reads as roughly 100× the real DeepSeek cost and would cut jobs off early.
configBRIDGE_CLAUDE_BINPath to the Claude Code binary.
configBRIDGE_JOB_ID
configBRIDGE_JOB_TIMEOUT_MSWall-clock ceiling (15 min). On expiry the job and its entire process tree are killed.
configBRIDGE_MAX_STEPSStep ceiling per job.
configBRIDGE_STATE_DIRJob snapshots, approval queue, audit log.
configDEEPSEEK_ALLOWED_ROOTSThree tools in two groups. All three are always registered — but until is set, the two agent tools reject every workspace with an explanatory error, so the bridge stays read-only.
🔐 secretDEEPSEEK_API_KEY1. Set to your key. Use a dedicated key for this bridge so it can be revoked independently, and set a spend cap on it in the DeepSeek console as a last line of defence.
configDEEPSEEK_BASE_URLOpenAI-compatible endpoint.
configDEEPSEEK_MAX_OUTPUT_TOKENSOutput cap. deepseek-flash is a reasoning model: reasoning_content and content share this budget, so a task that over-reasons can starve the answer.
configDEEPSEEK_MODELModel ID.
configDEEPSEEK_TIMEOUT_MSServer-side timeout; returns a structured error instead of hanging. Kept under Cloudflare's 100 s edge timeout.
configHOSTListen address. Leave on loopback — the tunnel runs on the same machine, so exposing the port to your LAN has no upside.
🔐 secretMCP_PATH_SECRETThis writes =<random hex> into .env (or prints it if .env doesn't exist yet).
configRATE_LIMIT_PER_MINUTEPer-IP sliding window. Limits the blast radius if the URL leaks.
Deployment configuration, supplied by whoever hosts the server. Users are not asked for these.
deployPORT
// quality suggestions

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

4/4 tools missing one or more hints — deepseek_flash (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); deepseek_agent_start (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); deepseek_agent_poll (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +1 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Tests exist

No test files found

Add tests that exercise each declared tool.

Secrets not logged

1 secret value sent to log

Redact or omit secret values from log output.

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail
The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.
// improvement guidance — verified publishers only
We have 4 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Score](https://m8ven.ai/badge/mcp/cassiatw1g/deepseek-mcp-bridge)](https://m8ven.ai/mcp/cassiatw1g/deepseek-mcp-bridge)
Shows your grade and updates automatically. Prefer no grade? Append ?variant=verified to the badge URL.
commit: 3769b2e48bb989931bea83a6d07b513a69638c1a
code hash: 5607624ffe8cc1ba6ea00fdb610d337d8dfd285c35ef0f5fbebabf701fd239b5
view raw JSON →
Check MCPs from inside your assistant
Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check
check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern
How to add it →Free · no account needed · works in any MCP client