MCP servers › io.github.madgodinc › mgi-mind

MCP server · registry snapshot 2026-10-23 · last tested 2026-10-23

io.github.madgodinc/mgi-mind

Local memory server for AI agents: hybrid search, a fact graph and a hash-chained audit log. — the publisher's description

8 of 9 record checks metRead-only · tools listed 2026-10-23Topic: ai-and-ml · AI-classifiedversion 2.8.2RustApache-2.0standard input/output29 tools

Summary

io.github.madgodinc/mgi-mind is a local MCP server listed in the official MCP registry at version 2.8.2. On 2026-10-23 ProtocolProbe started its published package in an isolated sandbox in read-only mode and read its inventory: 29 tools, 0 resources and 0 prompts.

Record checks

8 of 9 record checks met

met: Registry entry is active and says how to run it
met: Source repository link opens
met: Repository is not archived
met: Code pushed to the repository in the 90 days before our check
met: Repository publishes a security policy (SECURITY.md)
met: Package names its licence with a standard (SPDX) identifier
met: The version the registry lists can be installed and is not withdrawn
not met: npm package carries build provenance (attestation)
met: No known critical or high advisory in the package or its dependencies

Not ranked by downloads: no download figure available
Not ranked by stars: 9 stars (ranked from 10)

From public records, not a safety rating. Each check with its reason · Is it safe to install?

Key facts

Runs: local package
Transport: standard input/output
Package: npm · listed version current
License: Apache-2.0
Dependencies: no known high or critical advisories
Repository: public
Tools: 29
Described as changing data: 20 of 29 toolsAI-classified
Mainly works on: files and code on the machine it runs onAI-classified
Topic: ai-and-mlAI-classified
Last tested: 2026-10-23

Add to your client

Worth knowing before you connect it

20 tools are described as changing something (mind_visualize, mind_add, mind_provenance_add, …): our AI model's reading of the descriptions, not something we tested. We did not call them.

Each line comes from a section below, with its source and date.

How fresh this is

Live-tested

yes, a real session (not a text-only review)

Last tested

2026-10-23

Mode

read-only (no tool calls)

Latest version

2.8.2, published 2026-10-21 (registry, as of the 2026-10-23 snapshot)

First listed version

2026-10-20 (earliest version still in the registry; older removed versions would be earlier)

Version history

3 versions listed, 2026-10-20 to 2026-10-21; 3 in the 90 days before the 2026-10-23 snapshot.

Most recent 3 versions

2.8.2 · 2026-10-21
2.8.1 · 2026-10-20
2.8.0 · 2026-10-20

(versions still listed in the registry only)

Registry data

snapshot 2026-10-23

Package and repository

checked 2026-10-23

Engine

mcp-runtime-engine@0.1.0 · sdk@1.32.0

Changes since the last refresh

New in the registry: not in the list of 2026-10-04, listed on 2026-10-23 with version 2.8.2 (published 2026-10-21).

Source: the official MCP Registry list on 2026-10-04 and on 2026-10-23.

What it is

What does this server offer?

Observed inventory

29tools

0resources

0prompts

What it mainly works on, as our AI model read its tool descriptions: files and code on the machine it runs on.

20 of 29 tools are described as changing something (creating, editing, deleting, sending or running).

mind_searchon 1 other serverreads or searches
“Semantic (embedding) search across stored memories, ranked by relevance to `query`, with optional metadata filters.”
Publisher declares: read-only yes · open-world no
11 inputs, 1 required
- authorstring“Filter to memories written by this agent”
- created_beforestring“Only memories created before this instant, EXCLUSIVE (RFC3339 timestamp or YYYY-MM-DD date)”
- created_sincestring“Only memories created at/after this instant, INCLUSIVE (RFC3339 timestamp or YYYY-MM-DD date)”
- librariesarray“Filter to ANY of these libraries (OR).”
- librarystring“Filter to one library”
- limitnumber“Max results”
- querystringrequired“Search query”
- rerankboolean“Override the reranker for THIS query: true forces it on, false gives the raw hybrid (dense+sparse) order.”
- rerank_top_knumber“Override how many candidates the reranker re-orders for this query.”
- sourcestring“Filter by ingest source tag (e.g.”
- tiernumber“Retrieval tier: 1=facts, 2=summaries, 3=full”
mind_browsereads or searches
“Browse/list memories by metadata WITHOUT a search query: inventory, not ranking.”
Publisher declares: read-only yes · open-world no
8 inputs
- archivedstring“'only' lists ARCHIVED (soft-forgotten) memories so they can be restored; 'include' returns both archived and live.”
- authorstring“Only memories written by this agent”
- created_beforestring“Only memories created before this instant, EXCLUSIVE (RFC3339 or YYYY-MM-DD)”
- created_sincestring“Only memories created at/after this instant, INCLUSIVE (RFC3339 or YYYY-MM-DD)”
- librariesarray“List from ANY of these libraries (OR)”
- librarystring“List from one library”
- limitnumber“Max records”
- sourcestring“Only memories with this ingest source tag”
mind_recall_allreads or searches
“Unified recall across all memory types at once (facts + memories + procedures) for one query.”
Publisher declares: read-only yes · open-world no
2 inputs, 1 required
- limitnumber“Max per silo”
- querystringrequired“What to recall”
mind_should_searchreads or searches
“Decide whether to search memory BEFORE answering a user query.”
Publisher declares: read-only yes · open-world no
1 input, 1 required
- querystringrequired“The user's query to classify”
mind_visualizecontrols a browser or desktopdescribed as changing data
“Open the 3D memory visualization in the user's browser: the brain as glowing cores (memories, facts, regions) wired by neurons, with live pulses.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
Takes no inputs.
mind_addcreates or changes datadescribed as changing data
“Store free-text content as a searchable memory.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
3 inputs, 2 required
- contentstringrequired“Text to store, any length (chunked automatically if long).”
- librarystringrequired“Target library name.”
- sourcestring“Optional free-text provenance tag (e.g.”
mind_provenance_addcreates or changes datadescribed as changing data
“Persist an externally-sourced snippet (code, doc, RFC quote, commit message, etc.) into mgi-mind with a mandatory provenance citation.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
9 inputs, 3 required
- filestring“Optional path inside the repo.”
- langstring“Optional language tag (free string).”
- librarystring“Target library.”
- line_rangestring“Optional line range, e.g.”
- notestring“Optional one-liner the agent attaches (why this is worth keeping).”
- origin_urlstringrequired“https:// URL the snippet was lifted from.”
- repostring“Optional owner/repo when the source is a code host.”
- search_tool_usedstringrequired“Identifier of the search source the agent used in THIS session, e.g.”
- snippetstringrequired“Raw text to store.”
mind_doctordescribed as changing data
“Diagnose the local install: Qdrant reachable, embedding model and ONNX Runtime present, config valid.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world yes
1 input
- fixboolean“false (default): report problems only, no changes.”
mind_contexton 1 other serverreads or searchesdescribed as changing data
“Build a text briefing for session start: operating rule, pinned mind_block entries, skill catalogue, last session summary, library list, and up to 20 current knowledge-graph facts.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
Takes no inputs.
mind_ingestcreates or changes datadescribed as changing data
“Auto-ingest memory.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
3 inputs
- candidatesarray“Extracted items.”
- librarystring“Target library for memory candidates.”
- rawstring“Raw text for heuristic extraction (used only when candidates is omitted)”
mind_learncreates or changes datadescribed as changing data
“Record a procedural-memory lesson (error -> fix) for later mind_recall.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
5 inputs, 2 required
- contextstring“Short task description (drives semantic recall)”
- errorstringrequired“Error message / signature (will be normalized: paths, line numbers, addresses stripped)”
- fixstringrequired“What resolved it”
- provenancestring“Project / file where this applied”
- verifiedboolean“True ONLY if a deterministic check confirmed the fix”
mind_recallreads or searches
“Recall error->fix playbooks for an error that already happened, matched by error signature and/or task context.”
Publisher declares: read-only yes · open-world no
3 inputs
- contextstring“Task description to match (semantic)”
- errorstring“Error signature to match (lexical)”
- limitnumber“Max playbooks”

Show 17 more tools

mind_procedure_outcomecreates or changes datadescribed as changing data
“Record whether a procedure returned by mind_recall worked when reused.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
2 inputs, 2 required
- idstringrequired“Procedure id from mind_recall”
- workedbooleanrequired“Did the fix work this time”
mind_outcomecreates or changes datadescribed as changing data
“Record a typed external-signal outcome on any memory id, not only procedures: a test passed/failed, code compiled, a user confirmed/denied a fact, or a citing memory referenced this one.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
4 inputs, 2 required
- memory_idstringrequired“Target memory id (from mind_search or any tool returning ids)”
- signal_typestringrequired“What kind of signal this is.”
- sourcestring“Stable identifier of where the signal came from (e.g.”
- successboolean“Did the signal positively confirm the fact (true) or negate it (false)?”
mind_historyreads or searches
“List the most recently added memories (not facts, procedures, or skills), newest first by creation time.”
Publisher declares: read-only yes · open-world no
1 input
- limitnumber“Max entries to return, newest first.”
mind_consolidatereads or searches
“Preview what `mgimind consolidate` would do: count of exact duplicates, near-duplicates, and cold (old + unused) entries.”
Publisher declares: read-only yes · open-world no
1 input
- librarystring“Scope to one library (omit for all)”
mind_restorecreates or changes datadescribed as changing data
“Restore an ARCHIVED (soft-forgotten) memory by id, returning it to search.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
1 input, 1 required
- idstringrequired“Memory id of an archived entry”
mind_webreads or searchesdescribed as changing data
“Fetch a webpage and convert it to Markdown via the external `crw` tool.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
2 inputs, 1 required
- savestring“Library to store the page into.”
- urlstringrequired“URL to fetch”
mind_exportdeletesdescribed as changing data
“Export memories to disk, one file per library.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world no
2 inputs
- formatstring“json/md: one file per library with every memory.”
- outputstring“Output directory for json/md (one file per library) or output file path for instructions/profile.”
mind_importcreates or changes datadescribed as changing data
“Reconcile a directory of Markdown files (Obsidian vault or plain folder) into a library: the files on disk WIN, so a file that differs from what is already stored replaces the stored version.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world no
4 inputs, 1 required
- applyboolean“false (default): dry-run, only shows what would change.”
- librarystring“Target library name.”
- pathstringrequired“Directory to scan for .md files”
- sourcestring“File layout to expect.”
mind_statson 1 other serverreads or searches
“Read-only summary: memory count per library and total, knowledge-graph fact count (plus a dependants/confidence distribution when facts exist), session file count, and whether the vault is initialize…”
Publisher declares: read-only yes · open-world no
Takes no inputs.
mind_quarantinedeletesdescribed as changing data
“Inspect, promote, or expire entries that the relevance gate filtered into the quarantine layer.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world no
4 inputs, 1 required
- actionstringrequired“What to do”
- idstring“Required for action=show, promote, or expire”
- librarystring“Scope for action=list (optional)”
- limitnumber“Max entries for action=list”
mind_vaultreads or searches
“Vault is terminal-only by design.”
Publisher declares: read-only yes · open-world no
2 inputs, 1 required
- actionstringrequired“What instructions to render”
- keystring“Optional key name to interpolate into the instructions”
mind_sessioncreates or changes datadescribed as changing data
“Manage the agent's session record across runs.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
3 inputs, 1 required
- actionstringrequired“Lifecycle step”
- agentstring“Agent name; same across start/end”
- summarystring“Required for action=end.”
mind_factcreates or changes datadescribed as changing data
“Knowledge-graph facts (subject -> predicate -> object).”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
9 inputs, 1 required
- actionstringrequired“Operation”
- as_ofstring“With action=query: POINT-IN-TIME: return the facts that were CURRENT at this instant (RFC3339 or YYYY-MM-DD), time-travelling the superseded chain.”
- historyboolean“With action=query: return the SUPERSEDED history (past TemporalSingle values, oldest first) instead of current facts”
- idstring“Required for invalidate/restore (from action=query)”
- objectstring“Required for add, together with subject and predicate.”
- predicatestring“Required for add, together with subject and object.”
- subjectstring“add: the entity the triple is about, required together with predicate and object.”
- valid_fromstring“With action=add: optional, when this became true IN THE WORLD (RFC3339 or YYYY-MM-DD), as opposed to when it was recorded.”
- world_timeboolean“With action=query and as_of: use world-time (valid_from/valid_until) instead of record-time (created_at/valid_until).”
mind_librarycreates or changes datadescribed as changing data
“Library namespaces.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world no
4 inputs, 1 required
- actionstringrequired“Operation”
- idstring“Required for action=delete; memory uuid from search results”
- librarystring“Required for action=delete”
- namestring“Required for action=create”
mind_predicatecreates or changes datadescribed as changing data
“Register and inspect predicate cardinality (single | temporal-single | multi), which controls how mind_fact action="add" detects conflicts: Multi never conflicts; Single/TemporalSingle flag a conflic…”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
3 inputs, 1 required
- actionstringrequired“Operation.”
- cardinalitystring“Required for action=register.”
- predicatestring“Required for action=register and action=get.”
mind_blockcreates or changes datadescribed as changing data
“Pinned core-memory blocks (persona / user / current-project): a few small, named notes that are ALWAYS injected at the top of the session context, not ranked retrieval.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world no
3 inputs, 1 required
- actionstringrequired“Operation (default: list)”
- contentstring“Block content; required for action=set”
- namestring“Block name [a-z0-9_-]; required for set/get/remove”
mind_skillreads or searchesdescribed as changing data
“Skills: the house way of doing a kind of work, matched against the task you are ABOUT TO START (mind_recall is the other half: it answers an error that already happened).”
Publisher declares: read-only no · destructive yes · idempotent no · open-world no
8 inputs, 1 required
- actionstringrequired“Operation (default: list)”
- bodystring“The playbook itself, 8KB max; required for action=set”
- limitnumber“Max skills to return for action=match (default 3)”
- namestring“Skill name [a-z0-9_-]; required for set/show/remove/outcome”
- taskstring“What the work is; required for action=match”
- verifyboolean“action=outcome: promote to verified on success.”
- whenstring“What kind of task should surface this skill; required for action=set”
- workedboolean“action=outcome: did applying the skill work (default true)”

Each quoted sentence is the first sentence of the publisher’s own description. The kind of tool and the “changes data” mark are our AI model’s reading of that description, not something we tested: two differently worded runs had to agree, otherwise no label is shown, and nobody has checked them by hand. A tool without the “changes data” mark is described as only reading, searching or calculating, or the two runs did not agree. No tool was called. Read the publisher’s full description before relying on it. “Publisher declares” lists the hints the server itself sends with the tool (MCP annotations: read-only, destructive, idempotent, open-world); they are the publisher's claims, not checked by us. Inputs are the parameters in the tool's own input schema: name, declared type, whether it is required, and the first sentence of its description. Read 2026-10-23.

How well are its tools described?

Features #4 and #5

How clearly this server's own tool descriptions say what a tool does, and how consistent its tool list is. The first part is an AI model's yes/no reading of each description; the second part is counted. We do not turn it into a grade.

Descriptions

AI reading of each description

Says what the tool does: 100% of 29 tools
Says what it returns: 59% of 17 tools
States limits, defaults or errors: 25% of 28 tools
Says when to use it: 36% of 28 tools
Items covered per tool: 2.1 of 4 on average

Counted from the listing

Parameters with a description: 100% of 99
Tools with a description: 100% of 29
Typical description length: 423 characters

The tool set

Counted from the listing

Tools: 29
Size of the list: about 7,609 tokens for an agent to load (characters ÷ 4)
Naming: 29 of 29 names use snake_case

AI reading: easy to mix up

No pair found.

The AI items cover 29 of 29 tools: for a tool where two differently worded runs disagreed, that item is left out. They were not checked by hand, and no tool was called. “Easy to mix up” means two tools whose names or descriptions overlap without saying how they differ; the AI found none. We do not rate whether the tool set is complete or whether side effects are spelled out, because our AI reading of those was not reliable enough.

How do I add it to my client?

Config from the registry entry

From the npm package mgi-mind

Our sandbox started this package on 2026-10-23 (a read-only session: no tool was called).

Add to CursorAn install link in the format Cursor documents, holding the Cursor config below. The command runs the publisher’s code on your machine.

Claude Desktop · claude_desktop_config.json (Settings → Developer → Edit Config)

{
  "mcpServers": {
    "mgi-mind": {
      "command": "npx",
      "args": [
        "-y",
        "mgi-mind@2.8.2",
        "mcp"
      ]
    }
  }
}

Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json

{
  "mcpServers": {
    "mgi-mind": {
      "command": "npx",
      "args": [
        "-y",
        "mgi-mind@2.8.2",
        "mcp"
      ]
    }
  }
}

VS Code · .vscode/mcp.json

{
  "servers": {
    "mgi-mind": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "mgi-mind@2.8.2",
        "mcp"
      ]
    }
  }
}

VS Code (command line) · Bash or zsh terminal (macOS, Linux)

code --add-mcp '{"name":"mgi-mind","type":"stdio","command":"npx","args":["-y","mgi-mind@2.8.2","mcp"]}'

Claude Code

claude mcp add --transport stdio mgi-mind -- npx -y mgi-mind@2.8.2 mcp

Try it in the MCP Inspector · runs on your machine, opens in your browser · Node 22.19+

npx @modelcontextprotocol/inspector@2.11.0 -- npx -y mgi-mind@2.8.2 mcp

Arguments are written as the registry entry gives them; a named one as “--name value”, the form the registry documentation shows.
Optional settings the entry also lists (left out above): MGIMIND_HOME.
This runs the publisher's code on your machine (npx). Read its README first.
The MCP Inspector lists the server's tools, resources and prompts; a tool you call there runs for real.

Built from the server's registry entry with each client's documented format (checked 2026-10-14; the Cursor link and the VS Code command 2026-10-19; the MCP Inspector command 2026-10-21). Values in < > are yours to fill in; this page never contains a key. Where the server needs a setting the entry does not declare, it can still fail to start.

Can it be installed, and is it up to date?

Version pin · advisories

Listed version

Registry lists: 2.8.2
Latest stable: 2.8.2
Status: current
Withdrawn: no

Source: registry.npmjs.org · 2026-10-23. About the version the registry lists; a manual install may resolve to a different one.

Dependency advisories

Counted in the full dependency tree as resolved on 2026-10-23 (npm audit). Bars share one scale. The package itself has no known vulnerability (OSV.dev).

Integrity, provenance, license

Integrity: sha512-j0tb03rDPy8ZEN4hQ…
Signature: signed
License: Apache-2.0

Source: the package registry · 2026-10-23.

Does the registry listing match what we found?

Feature #6

The registry verifies a package once, when it is published, and does not re-check it. A difference below is about the listing, not a judgement of the publisher.

Registry says	We found	Result	Source · date
Published package can be started	Started and answered	matches	our test · 2026-10-23
Version 2.8.2 on npm	Exists and can be installed	matches	npm · 2026-10-23
Repository github.com/madgodinc/mgi-mind	Opens publicly	matches	api.github.com · 2026-10-23

Who made it?

Feature #7 · lineage

Facts about the publisher. We do not turn them into a trust score.

Namespace: io.github.madgodinc
GitHub owner: a personal account (madgodinc)
Build record: signed

Repository: github.com/madgodinc/mgi-mind
Stars: 9
Repository age: 91–180 days
Last push: 0–30 days ago
Archived: no
Security policy: SECURITY.md

Source: the registry entry and api.github.com · 2026-10-23; security policy read from GitHub · 2026-10-23.

Publish this server? Run these checks against it yourself before release, from your own machine: a server the command starts, or your own server at its URL after a one-time proof that you control it: npx protocolprobe-selftest.

Choosing

Record checks

Public records · not a safety rating

8 of 9 record checks met

Not ranked by downloads: no download figure available
Not ranked by stars: 9 stars (ranked from 10)

MetRegistry entry is active and says how to run itActive, with a package or a remote address.
MetSource repository link opensThe linked GitHub repository is public.
MetRepository is not archivedNot archived.
MetCode pushed to the repository in the 90 days before our checkLast push 0-30 days before our check.
MetRepository publishes a security policy (SECURITY.md)SECURITY.md found.
MetPackage names its licence with a standard (SPDX) identifierApache-2.0
MetThe version the registry lists can be installed and is not withdrawnThe listed version exists and is current.
Not metnpm package carries build provenance (attestation)Signed by npm, but no build attestation.
MetNo known critical or high advisory in the package or its dependenciesNone known in the package or its dependency tree.

Read from public records only: the registry entry, npm/PyPI, GitHub and advisory databases, checked 2026-10-23. No tool was called. Only “met” and “not met” are counted, so the total differs between servers; a check that does not apply or that we could not run is listed, never counted against it. It is not a safety rating. How each check works · Leaderboards

Common questions about io.github.madgodinc/mgi-mind

Answered from the data above

Is io.github.madgodinc/mgi-mind safe to install?

We do not rate servers as safe or unsafe. 8 of its 9 applicable record checks are met (facts from public records, each listed on this page). What the records show: Its source repository opens publicly. Its repository had a push in the last 90 days. The listed version is the latest stable release. The package itself has no known vulnerability (OSV.dev). Its full dependency tree has no known advisory. 20 of its tools describe changing data (our AI model's reading of the descriptions). These are facts with their sources on this page, not a safety guarantee, and we did not run its tools.

Has io.github.madgodinc/mgi-mind been security tested?

Partly. 2 of the 12 checks that apply to it were exercised. We started the package in an isolated sandbox and read what it declares, but this test round was read-only, so its tools were not called. No security verdict is published before verification.

What can io.github.madgodinc/mgi-mind do?

It lists 29 tools. In our AI model's reading of their descriptions (two runs had to agree, nobody checked it by hand), they include tools that read or search, create or change data, delete and control a browser or desktop. We did not call any tool, so this describes the text, not the behaviour.

Can io.github.madgodinc/mgi-mind change or delete data?

20 of its tools say in their description that they create, edit, delete, send or run something (our AI model's reading). We did not call any tool, so we cannot say what actually happens.

Does io.github.madgodinc/mgi-mind publish a security policy?

Yes: its repository has a public security policy (github.com/madgodinc/mgi-mind/blob/HEAD/SECURITY.md). That is the publisher's statement, not permission for us to test the server, and we call none of its tools.

Is the listed version current?

Yes. The registry lists 2.8.2, the latest stable release on npm.

Where is the source code of io.github.madgodinc/mgi-mind?

In github.com/madgodinc/mgi-mind, which opens publicly.

Found this page useful?

Anonymous · no sign-in

A quick, anonymous reaction — no account, no email. One per kind from your browser. The tally updates when the page is next refreshed, and it is only a rough count, never a safety rating or a measured number of people.

Similar servers

Same topic · AI-read

com.wingmanprotocol.agent/gatewayalso has tools that controls a browser or desktop, creates or changes data, deletes, reads or searchescompare with this one
io.github.MaxFreedomPollard/compartmentCompartmentalso has tools that creates or changes data, deletes, reads or searchescompare with this one
io.github.Lyellr88/marm-mcp-serveralso has tools that creates or changes data, deletes, reads or searchescompare with this one
io.github.varun29ankuS/shodh-memoryalso has tools that creates or changes data, deletes, reads or searchescompare with this one
io.github.qualixar/superlocalmemorySuperLocalMemoryalso has tools that creates or changes data, deletes, reads or searchescompare with this one
io.github.Intina47/context-syncalso has tools that creates or changes data, deletes, reads or searchescompare with this one

Active servers whose topic is also “ai-and-ml” and that have at least one tool of the same kind; most kinds in common first, then most GitHub stars. The topic and the tool kinds are an AI model's reading of the publishers' descriptions, not checked by hand. Similar is not a recommendation.

Compare with another server

Side by side: registry entry, our read-only session, the tools and the 18 classification fields. Same values as each page; no score.

Security testing

What did we test, and what did we leave out?

18 checks · features #1, #2

Not probed (read-only run)

We started the package in an isolated sandbox and read what it declares, but this test round was read-only, so its tools were not called. No security score is given; a check we did not run is never counted as passed.

The 18 checks at a glanceour test · 2026-10-23

Inventory: exercised
Hidden instructions: exercised
Real execution: not run · our policy
Secret leak: not run · nothing to check it against
Internal addresses: not run · our policy
Unconfirmed changes: not run · our policy
Bad input: not run · our policy
Model requests: not run · nothing to check it against
Sensitive questions: not run · nothing to check it against
Folder boundary: not run · our policy
Log leaks: not run · nothing to check it against
Hidden content: not run · nothing to check it against
Fake assistant turns: not applicable
Token passthrough: not applicable
Token audience: not applicable
Sign-in redirect: not applicable
Consent handling: not applicable
Sign-in metadata: not applicable

2 exercised10 not run (reason given)6 not applicable

Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 2 of the 12 checks that apply to it were exercised. We do not publish security-check outcomes for named servers.

Exercised · 2

1Inventory
tool-listReads the declared tools, resources and prompts.exercised
2Hidden instructions
description-poisoningLooks for hidden instructions in tool descriptions.exercised

Not run, with the reason · 10

3Real execution
real-executionCalls a tool and checks what really happens.This check calls the package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.not run · our policy
4Secret leak
canary-leakPlants a fake secret and checks whether it leaks.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
5Internal addresses
ssrfChecks whether a tool can be steered to internal addresses.This check calls the package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.not run · our policy
6Unconfirmed changes
write-without-confirmationChecks whether tools that change data act without asking.This check calls the package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.not run · our policy
7Bad input
error-handlingSends bad input and watches how the server answers.This check calls the package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.not run · our policy
8Model requests
samplingChecks whether the server asks the client's model to act for it.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
9Sensitive questions
elicitation-sensitive-dataChecks whether the server asks users for sensitive data.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
10Folder boundary
root-boundaryChecks whether the server reaches outside the folders it was given.This check calls the package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.not run · our policy
11Log leaks
logging-side-channelChecks whether log messages carry data they should not.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
12Hidden content
audience-hidingChecks resources that hide content from the user.This check needs content the server returns, and nothing was read or called.not run · nothing to check it against

Does not apply to this server · 6

13Fake assistant turns
fake-assistant-turnChecks prompts that pose as the assistant's own words.The server exposes no prompts.not applicable
14Token passthrough
token-passthroughChecks whether the server forwards a user's token to other services.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable
15Token audience
token-audience-validationChecks whether tokens meant for another service are accepted.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable
16Sign-in redirect
open-redirectChecks the sign-in redirect for abuse.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable
17Consent handling
confused-deputyChecks consent handling when one service acts for another.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable
18Sign-in metadata
oauth-url-schemeChecks the published sign-in metadata for unsafe URLs.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable

Source: our own test in an isolated sandbox, 2026-10-23, mcp-runtime-engine@0.1.0. Which checks count and why follows our published scoring model.

What happened during the test?

Feature #8

The steps in order, as the test record holds them.

0 msStarted the published package in an isolated sandbox (read-only mode)
2,643 msConnected after 0 redirects.
Read the inventory: 29 tools, 0 resources, 0 prompts.
3,584 msFinished: 2 checks exercised.

Reference

How is it classified?

18 fields

One value per field, each with its source. Fields written by AI models are marked. A field with no value says why.

TopicAI-classified

ai-and-ml

AI-classified · 2026-10-23

Pricing modelAI-classified

no value

The website listed in the registry is a code-hosting, package or marketplace page, not the product's own site.

Programming language

Rust

api.github.com · 2026-10-23

Hosting type

local package

registry · 2026-10-23

MCP capability

tools

our test · 2026-10-23

Transport

standard input/output

registry · 2026-10-23

Required credentials

none declared

registry · no declaration is not a guarantee

Package registry

npm

registry · 2026-10-23

Freshness

0–30 days

registry updatedAt · 2026-10-23

Lifecycle status

active

registry · 2026-10-23

License class

permissive

package registry · 2026-10-23

Integrity hash

declared (sri)

package registry · 2026-10-23

Signature / provenance

signed

package registry · 2026-10-23

Dependency advisories

none known

npm audit · 2026-10-23

Popularity

not known (our limit)

Our lookup failed (network error, timeout or rate limit). This is our limit, not the server's.

Publisher signals

owner: a personal account · repository age: 91–180 days · stars: 0–9 · build record: signed

api.github.com · 2026-10-23

Maintenance

active

api.github.com · 2026-10-23

Environment

your machine

where it runs, from the hosting type

“Not stated” means the source did not state it; “does not apply” means it does not apply to this kind of server; “our limit” means our own lookup failed. A linked value opens the directory filtered to the same value.

Cite or correct this page

Sources and corrections

Suggested citation

ProtocolProbe. “io.github.madgodinc/mgi-mind: MCP server record.” Data checked 2026-10-23. https://protocolprobe.com/mcp/servers/io.github.madgodinc/mgi-mind

Figures are valid for the date shown. Our facts on this page are CC BY 4.0: reuse them with a link and the check date. Quoted text (the publisher’s descriptions, website quotes, tool names) is not ours to license.

As JSON: this record in the API · API documentation.

Badge for your README

[![ProtocolProbe](https://protocolprobe.com/api/v1/badge/io.github.madgodinc/mgi-mind)](https://protocolprobe.com/mcp/servers/io.github.madgodinc/mgi-mind)

It shows this server's record-check count: facts from public records, no tool called. It is not a security rating or a pass. It links here and updates after each data reload.

Something wrong, or is this yours?

If a fact here is wrong, tell us and we will re-check it. If you operate this server, you can run our checks on it yourself with the free self-test command; we call no server’s tools ourselves for anything shown here.

Write to hello@protocolprobe.com · corrections log · methodology