sakana-mcp (sandraschi/sakana-mcp) is an MCP server listed on the M8ven Trust Index. It scores 73 out of 100, grade C. It declares 6 tools. No publisher has claimed this listing.

Back to MCP Trust IndexM8ven
C
Caution
73/100

sakana-mcp

MCP server that wraps Sakana AI Scientist v2 so MCP Client (claude, cursor...) can act as a research director for autonomous scientific loops.

→ sandraschi/sakana-mcp· listed on github_repo_search

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

sandraschi

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
⚠️
Tool descriptions don’t match what handlers do
1 tool describes read intent but its handler mutates — research_ideate (line 259: workshop_path.write_text()
✅
No credential exfiltration, no sensitive file access, no obfuscation
Static analysis found nothing flowing your secrets to unexpected places.
✅
Open source with a license and README
Anyone can audit the code, the license is declared, and the publisher documents what it does.
🔐
You'll be asked for 2 credentials: GEMINI_API_KEY, S2_API_KEY
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// tools this server exposes6 tools

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.

research_ideate

RESEARCH_IDEATE — Generate 5 research hypotheses via Progressive Agentic Tree Search.

research_execute

RESEARCH_EXECUTE — Launch AI Scientist experiment manager in Docker sandbox.

research_status

RESEARCH_STATUS — Monitor tree health from latest run artifacts.

research_review

RESEARCH_REVIEW — Run VLM feedback loop over manuscript figures/captions.

research_library

RESEARCH_LIBRARY — List sample and custom research tasks.

research_workflow_plan

RESEARCH_WORKFLOW_PLAN — Build a guided agentic workflow plan for a task.

// 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.
configRESEARCH_VAULT_PATHoptional; defaults to ./research_vault
configAI_SCIENTIST_V2_PATHoptional; defaults to ./vendor/ai-scientist-v2
🔐 secretGEMINI_API_KEYrequired for Gemini-backed ideation/review paths
🔐 secretS2_API_KEYSemantic Scholar key for literature-heavy workflows
configMCP_CENTRAL_DOCS
// 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

6/6 tools missing one or more hints — research_ideate (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); research_execute (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); research_status (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +3 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.

Descriptions match behaviour

1 tool describes read intent but its handler mutates — research_ideate (line 259: workshop_path.write_text()

Rename the tool, rewrite the description, or move the side-effect into a separate clearly-named tool.

Tool test coverage

Only 0/6 tools referenced in tests (0%)

Write tests that reference each tool by name so every tool has at least one test.

Tool description accuracy

research_ideate: description implies read-only but handler writes/deletes/executes

Update tool descriptions to accurately reflect all capabilities — especially write, delete, or execute operations.

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 5 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/sandraschi/sakana-mcp?variant=verified)](https://m8ven.ai/mcp/sandraschi/sakana-mcp)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: 1cdea472f6541dd5e09ff16dc7b1af5cd9afa75b
code hash: 023fc84fcb7fc60156c79967ff811dbaeb4e1d7c89c20c80bf2ea7aa5e09cd7c
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