C
Emerging
74/100
3 days ago

minni

Local-first memory and governance layer for AI agents, with per-agent vaults, hybrid recall, review-first learning, handoffs, audit trails, and native AFM/bridge provider support.

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

infektyd

Source: github_code

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 →

Install from

M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.

// key findings
No credential exfiltration, no sensitive file access, no obfuscation
Static analysis found nothing flowing your secrets to unexpected places.
🔐
You'll be asked for 1 credential: MINNI_CONSOLE_TOKEN
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.
configCLAUDE_CONTEXT_WINDOW
configCODEX_CONTEXT_WINDOW
configCURSOR_CONTEXT_WINDOW
configDEEP_RESEARCH_AGENT_ROOT
configDEEP_RESEARCH_CLI
configDEEP_RESEARCH_PYTHON
configGEMINI_CONTEXT_WINDOW
configGROK_CONTEXT_WINDOW
configKILO_CONTEXT_WINDOW
configMINNI_AFM_ADAPTER_ID; status reports only adapterConfigured, never the
configMINNI_AFM_ADAPTER_PATHcontract. Adapter configuration is indicated with or
configMINNI_AFM_ALLOWED_TARGETSand MINNI_MODEL_ALLOWED_TARGETS (provider-protocol
configMINNI_AFM_HEALTH_URLAFM health URL: if set, otherwise http://127.0.0.1:11437/health.
configMINNI_AFM_INPUT_BUDGET_TOKENS
configMINNI_AFM_MODE
configMINNI_AFM_NATIVE_HELPERSet to an executable JSON helper to let native
configMINNI_AFM_PREPARE_TASK_MODELAFM prepare-task model: if set, otherwise apple-foundation-models.
configMINNI_AFM_PREPARE_TASK_URLAFM prepare-task URL: if set, otherwise http://127.0.0.1:11437/v1/chat/completions.
configMINNI_AFM_PROBE_CACHE
configMINNI_AFM_PROBE_TIMEOUT
configMINNI_AFM_PROVIDER_MODEAFM provider mode: bridge by default; set =native, auto, or off to change opt-in AFM calls.
configMINNI_AGENT_IDVault: ~/.minni/claudecode-vault (override: MINNI_CLAUDECODE_VAULT_PATH). The manifest pins =claude-code, MINNI_VAULT_PATH=~/.minni/claudecode-vault, and MINNI_SOCKET_PATH=~/.minni/run/minnid.sock.
configMINNI_AGENT_VAULTS
configMINNI_BYPASS_AUDIT_LIMIT
configMINNI_CLAUDECODE_AGENT_IDAgent identity: claude-code (override: ).
configMINNI_CLAUDECODE_HOOKSDisable hooks without uninstalling: export =off.
configMINNI_CLAUDECODE_VAULT_PATHClaude Code vault: , otherwise ~/.minni/claudecode-vault.
configMINNI_CLAUDECODE_WORKSPACE_ID
configMINNI_CODEX_AGENT_IDprincipal (MINNI_AGENT_ID, with as a Codex-scoped
configMINNI_CODEX_CONTEXT_WINDOW
configMINNI_CODEX_HOOKS
configMINNI_CODEX_VAULT_PATHCodex vault: MINNI_VAULT_PATH (or legacy fallback ), otherwise ~/.minni/unknown-vault. The Codex surface normally sets MINNI_VAULT_PATH=~/.minni/codex-vault in its manifest env.
configMINNI_CODEX_WORKSPACE_ID
configMINNI_CONSOLE_DEEP_RESEARCH
configMINNI_CONSOLE_NO_AUTH
🔐 secretMINNI_CONSOLE_TOKEN
configMINNI_CURSOR_AGENT_ID
configMINNI_CURSOR_CONTEXT_WINDOW
configMINNI_CURSOR_HOOKS
configMINNI_CURSOR_VAULT_PATH
configMINNI_CURSOR_WORKSPACE_ID
configMINNI_GEMINI_AGENT_ID
configMINNI_GEMINI_CONTEXT_WINDOW
configMINNI_GEMINI_HOOKS
configMINNI_GEMINI_VAULT_PATH
configMINNI_GEMINI_WORKSPACE_ID
configMINNI_GROK_AGENT_ID
configMINNI_GROK_CONTEXT_WINDOW
configMINNI_GROK_HOOKS
configMINNI_GROK_VAULT_PATHGrok Build vault: , otherwise ~/.minni/grok-build-vault.
configMINNI_GROK_WORKSPACE_ID
configMINNI_HOMEfor the AFM adapter vars). overrides the home directory for every
configMINNI_INBOX_HANDOFF_TTL_DAYS
configMINNI_KILOCODE_AGENT_IDAgent identity: kilocode (override: ).
configMINNI_KILOCODE_HOOKSDisable hooks without uninstalling: export =off.
configMINNI_KILOCODE_VAULT_PATHKiloCode vault: , otherwise ~/.minni/kilocode-vault.
configMINNI_KILOCODE_WORKSPACE_ID
configMINNI_MODEL_ALLOWED_TARGETSMINNI_AFM_ALLOWED_TARGETS and (provider-protocol
configMINNI_PLAN_HISTORY_CAP
configMINNI_PROVIDERS_CONFIG~/.minni/providers.json (override with ) configures
configMINNI_RECALL_GUARD_MODE
configMINNI_RESOLVE_OPERATORS
configMINNI_SOCKET_PATHDaemon socket: if set, otherwise ~/.minni/run/minnid.sock.
configMINNI_UI_HOST
configMINNI_UI_PORT
configMINNI_VAULT_PATHCodex vault: (or legacy fallback MINNI_CODEX_VAULT_PATH), otherwise ~/.minni/unknown-vault. The Codex surface normally sets MINNI_VAULT_PATH=~/.minni/codex-vault in its manifest env.
configMINNI_WORKSPACE_ID
// 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

37/37 tools missing one or more hints — minni_prepare_task (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); minni_prepare_outcome (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); minni_team_runtime (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +34 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.

Tool inputs are validated

34/37 tool handlers declare input schemas (92%)

Declare an inputSchema with zod/joi/yup on every tool definition.

License file

No license file

Add a LICENSE file (MIT, Apache-2.0, etc.).

Shell command execution

4 child_process/subprocess calls in production code — runs shell commands (src/ui-server.ts:345, kilo/minni-plugin.js:297, kilo/minni-plugin.js:439)

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

Secrets not logged

1 secret value sent to console.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 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 Score](https://m8ven.ai/badge/mcp/infektyd-minni-zh899g)](https://m8ven.ai/mcp/infektyd-minni-zh899g)
Shows your grade and updates automatically. Prefer no grade? Append ?variant=verified to the badge URL.
commit: 4ceba4d359cb65e2a9b6cd898dec1d56248b0282
code hash: dcd226e361b970660f0ca622f67c649d2bdd8cddd33ee5e14db55c5941f73756
verified: 8/18/2026, 3:54:46 PM
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