minsky (edobry/minsky) is an MCP server listed on the M8ven Trust Index. It scores 52 out of 100, grade D. It declares 32 tools. No publisher has claimed this listing.

Caution

52/100

minsky

Item: minsky
Rating: 52
Author: M8ven

The engineering organization around your AI agents — tasks, isolated sessions, adversarial review, memory, and decision routing, built as environment.

→ edobry/minsky · 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 push why connect →

Who stands behind it

edobry

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

⚠️

Known vulnerabilities in dependencies: 7 high

Affects packages this MCP installs at runtime. Upgrade or remove the affected dependency.

✅

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 1 credential: MINSKY_MCP_AUTH_TOKEN

These are read from process.env at runtime. Make sure you trust where they’ll be sent.

// tools this server exposes32 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.

search

Semantic search across indexed knowledge bases. Returns ranked results with excerpts.

fetch

Live-fetch a single document from a configured knowledge source by ID.

sources

List configured knowledge sources with their sync status.

sync

Sync one or all configured knowledge sources into the vector index.

list

create

update

similar

supersede

lineage

open

Explicitly open a named attention window. Emits a Postgres NOTIFY event.

close

Explicitly close a named attention window. Emits a Postgres NOTIFY event.

status

Show currently-open attention windows with one-line summary per window

service

Load the pending-ask cohort for a window, render a terminal digest, and accept operator responses

session.edit_file

Use this tool to make an edit to an existing file. This will be read by a less intelligent model, which will quickly apply the edit. You should make it clear what the edit is, while also minimizing the unchanged code you write. When writing the edit, you should specify each edit in sequence, with t…

session.search_replace

Replace text in a file within a session workspace. By default, requires exactly one occurrence (for safety). Set replace_all=true to replace all occurrences. FAIL-CLOSED (mt#2400): a replace_all matching 2+ occurrences that would grow the file beyond 1.5x its original size is REFUSED as a likely run…

tasks.spec.patch

Edit a task specification using marker-based patching. Task specs are stored in the database, not the filesystem. Use this tool to make partial edits to a task spec. Specify each edit with the special comment // ... existing code ... to represent unchanged content between edited sections. For exam…

tasks.spec.search_replace

Replace a single occurrence of text in a task specification. Task specs are stored in the database, not the filesystem.

session.move_file

Move a file from one location to another within a session workspace

session.rename_file

Rename a file within a session workspace

session.read_file

Read a file within a session workspace with optional line range support

session.write_file

Write content to a file within a session workspace

session.list_directory

List contents of a directory within a session workspace

session.file_exists

Check if a file or directory exists within a session workspace

session.delete_file

Delete a file within a session workspace

session.create_directory

Create a directory within a session workspace

session.grep_search

Search for patterns in files within a session workspace using regex

session.diff

Show git diff output for a session workspace. Returns unstaged changes by default, or staged changes with staged=true.

session.status

restart

Restart the local MCP daemon (the tray respawns it). Previews by default; pass --execute to act.

register

index-embeddings

Generate and store embeddings for tools (tool_embeddings)

// known CVEs in dependencies7 high4 medium6 low

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

highdrizzle-orm@0.44.2GHSA-gpj5-g38j-94v9

Drizzle ORM has SQL injection via improperly escaped SQL identifiers

highglob@11.0.3GHSA-5j98-mcp5-4vw2

glob CLI: Command injection via -c/--cmd executes matches with shell:true

highws@8.18.3GHSA-96hv-2xvq-fx4p

ws: Memory exhaustion DoS from tiny fragments and data chunks

high@modelcontextprotocol/inspector@0.16.2GHSA-g9hg-qhmf-q45m

MCP Inspector is Vulnerable to Potential Command Execution via XSS When Connecting to an Untrusted MCP Server

highpostcss@8.5.3GHSA-6g55-p6wh-862q

PostCSS: Arbitrary file read and information disclosure via attacker-controlled sourceMappingURL in CSS comments

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.

configCC_CONVERSATION_ID

configCLAUDE_CODE_ENTRYPOINT

configCLAUDE_CODE_SESSION_ID

configMINSKY_COCKPIT_ORIGIN

configMINSKY_COCKPIT_RP_ID

configMINSKY_HOME

🔐 secretMINSKY_MCP_AUTH_TOKEN

configMINSKY_MCP_INIT_RETRY_INTERVAL_MS

configMINSKY_MCP_MAX_SESSIONS

configMINSKY_MCP_MEMORY_ENRICHMENT

configMINSKY_MCP_MEMORY_ENRICHMENT_TIMEOUT_MS

configMINSKY_MCP_RETRY_AFTER_SECS

configMINSKY_MCP_SESSION_IDLE_TIMEOUT_MS

configMINSKY_MCP_SESSION_REAPER_INTERVAL_MS

configMINSKY_STATE_DIR

configPG_DRAIN_TIMEOUT_MS

// 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

32/32 tools missing one or more hints — search (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); fetch (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); sources (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +29 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.

Shell command execution

4 calls in production code run through a shell (src/commands/lint/index.ts:52, src/mcp/daemon-state.ts:114, src/mcp/staleness-detector.ts:153)

Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.

No arbitrary install scripts

Has postinstall/preinstall script — runs arbitrary code on npm install

Remove postinstall/preinstall hooks unless they’re essential.

Production dependencies are patched

0 critical, 3 high severity in production deps — drizzle-orm@0.44.2 (high), glob@11.0.3 (high)

Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.

Dev dependencies

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

Upgrade dev dependencies when convenient.

Dependency freshness

9/65 production deps abandoned (no release in 2+ years): @types/logform@2022-04-07 (4.4y), @types/winston@2022-06-13 (4.3y), d3-force@2022-06-14 (4.3y)

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 6 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/edobry/minsky?variant=verified)](https://m8ven.ai/mcp/edobry/minsky)

Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.

commit: 4636c05be1a0ee9b3ece58cab51655f6b23d4b6f

code hash: fed57f58e63e730b972f25e7ffae29c9e2411efd469ff72ef2df047d095a1513

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