mistral-mcp (Swih/mistral-mcp) is an MCP server listed on the M8ven Trust Index. It scores 70 out of 100, grade C. It declares 35 tools. No publisher has claimed this listing.

Back to MCP Trust IndexM8ven
C
Caution
70/100

mistral-mcp

Full Mistral AI MCP server — OCR, Voxtral audio, Codestral FIM, durable workflows, document extraction — for Claude Code, Cursor, Windsurf, Zed, Mistral Connectors

→ Swih/mistral-mcp· listed on glama

Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we 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

Swih

Source: Glama · also listed on 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

Glamanot scored hereGitHub

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
⚠️
Tool annotations don’t match behaviour
1 read-only tool performs write/delete/exec — process_document (line 473: mkdirSync(sub, { recursive: true }))
🚨
Known vulnerabilities in dependencies: 1 critical
Affects packages this MCP installs at runtime. Upgrade or remove the affected dependency.
🔐
You'll be asked for 1 credential: MISTRAL_API_KEY
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// tools this server exposes44 tools · 9 behind config

These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.

mistral_agent
mistral_moderate
mistral_classify
batch_create
batch_get
batch_list

List batch jobs with optional filters.

batch_cancel

Request cancellation of a running batch job. Completed requests still count for billing.

connectors_list
connectors_get
connectors_list_tools
connectors_call_tool
conversation_start
conversation_append
conversation_get

Fetch a conversation's configuration (model/agent, tools, instructions).

conversation_list

List conversations created with this API key, most recent first.

conversation_history
conversation_delete

Permanently delete a conversation and its history.

process_document
files_upload
files_list
files_get

Retrieve a single file's metadata by id.

files_delete

Delete a file by id. This is irreversible.

files_signed_url
libraries_list
libraries_get

Fetch a Library's metadata (owner, size, document count).

libraries_documents_list

List the documents uploaded to a Library, with their processing status.

libraries_documents_upload
libraries_documents_status

Check whether an uploaded document has finished processing and is searchable.

rag_indexes_list
workflow_execute
workflow_status
workflow_interact
workflow_deployments_list
workflow_runs_list
workflow_stop
voxtral_transcribebehind config
voxtral_speakbehind config
mistral_tool_callbehind config
codestral_fimbehind config
mistral_visionbehind config
mistral_ocrbehind config
mistral_chatbehind config
mistral_chat_streambehind config
mistral_embedbehind config
// known CVEs in dependencies1 critical

Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.

criticalvitest@2.1.9GHSA-5xrq-8626-4rwp

When Vitest UI server is listening, arbitrary file can be read and executed

Depend on this server? Get alerted when its CVEs change.Watch this server free →
// 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.
🔐 secretMISTRAL_API_KEYTest pyramid: unit → contract → stdio e2e → live API (requires ).
configMISTRAL_DEFAULT_MODEL
configMISTRAL_MCP_CACHE_DIRprocess_document cache configurable per-call and via , with a retention window (MISTRAL_MCP_CACHE_TTL_HOURS, default 7 days, 0 to disable) after which entries are deleted, not merely bypassed
configMISTRAL_MCP_CACHE_TTL_HOURSprocess_document cache configurable per-call and via MISTRAL_MCP_CACHE_DIR, with a retention window (, default 7 days, 0 to disable) after which entries are deleted, not merely bypassed
// quality suggestions

Tool annotations match behaviour

1 read-only tool performs write/delete/exec — process_document (line 473: mkdirSync(sub, { recursive: true }))

Either remove the readOnlyHint:true annotation, or remove the write/delete call from the tool handler.

Destructive tools are labelled

1 tool perform destructive updates without destructiveHint — process_document deletes at line 493 (unlinkSync(path))

Add destructiveHint:true to any tool whose handler calls .delete(), .upsert(), .update(), unlink, rm, DELETE, DROP, REPLACE INTO, or any operation that overwrites existing data.

Dev dependencies

1 critical/high in dev-only deps (does not ship to users)

Upgrade dev dependencies when convenient.

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 3 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 Verified](https://m8ven.ai/badge/mcp/swih/mistral-mcp?variant=verified)](https://m8ven.ai/mcp/swih/mistral-mcp)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: c2bb12f27b793149cc14074b2b1141f86e5d5eac
code hash: 49339e66a9504a8f6939c3c9bbf5f8b2aee054a7167a3b0e7288a944e0971564
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