Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

cogito-mem (Cogi)

PYPI · COGITO-MEM

Local long-term memory for Claude Code and other agents: every message kept word for word, no cloud.

Available components

81 Trust /100

Last scanned (15 hours ago)

Scores higher than 81% of PyPI servers

Category Memory and Knowledge

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security100
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • Runs hatchling.build at install time, a recognised build step with no custom scripting around it. View diagnostics → Pass
  • 0 of 1 dependencies flagged as unhealthy. View diagnostics → Pass
Provenance & Transparency97
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • Cryptographically verified build provenance (signed, bound to meridian21lab/cogito-mem). View diagnostics → Pass
  • Clear OSI-approved license (MIT).Pass
  • Actively maintained (last published 0 days ago).Pass
  • Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability68
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 472 tokens (~236/item across 2 items; 2 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management7
  • Stability observed for 2 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 2 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 3 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 22 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

  • 21 Oct 26 +15
    • Tool safety: pass → unverified ▼ security
    • Malware scan: unverified → pass ▲ security
    • Stability: Stability not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet. security
    • Capabilities: pass → unverified ▼ functional
    • Tool coverage: 100 → unverified ▼ functional
    • Stability: unverified → 0.03 ▲ functional
    • First check of Schema quality: unverified functional
    • Package version: 0.2.0 → 0.2.1 functional
  • 20 Oct 26 65

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 22 Oct 2026 · Analysed pypi/cogito-mem@0.2.1

Provenance Verified

A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.

Result Verified
Ecosystem pypi
Reason Verified
Discovered via Registry attestation endpoint
Source repo meridian21lab/cogito-mem
Certificate issuer https://token.actions.githubusercontent.com
Certificate SAN https://github.com/meridian21lab/cogito-mem/.github/workflows/release.yml@refs/tags/v0.2.1
Rekor log index 3363008514
Predicate type PyPI publish attestation https://docs.pypi.org/attestations/publish/v1
Subject digest sha256:8b8fb8b085583eb79bddeccd5f70090774915e1939d1547b617143a894d188b7

Background: How many MCP packages publish verified provenance →

Install scripts 1 script
Hook Tier Command
build_backend allowlisted hatchling.build

Background: Why install scripts are a supply-chain risk →

Dependencies 1 package
Packages resolved 1
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 2 exposed · ~323 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
memory_append ~91

Save a note to the user's long-term memory: an idea, a decision, an open question or a fact the user stated. Write it so it makes sense on its own later. It is stored word for word with the current time and cannot be edited.

NameTypeReqDescription
textstringyesThe note, word for word.
titlestring–Optional short title, e.g. the project or topic.

No output schema declared.

No examples provided.

memory_query ~232

Search the user's long-term memory of earlier chats and sessions. Returns the few stored messages that best match, each with valid_at (when it was said) and a source pointing to the original message. Turn time phrases into valid_after (inclusive) and valid_before (exclusive): for 'a week ago' use a window of a few days around that date, for 'last month' that month. Today is Wednesday 2026-10-21 (UTC); the response's as_of is the current time.

NameTypeReqDescription
max_tokensinteger–Reading budget for the returned text, in tokens (default 1000).
textstringyesWhat to look for, in the user's own words.
valid_afterstring–Only items said at or after this RFC 3339 time with a time zone, e.g. 2026-10-11T00:00:00Z.
valid_beforestring–Only items said before this RFC 3339 time with a time zone, e.g. 2026-10-11T00:00:00Z.

No output schema declared.

No examples provided.

Install

How do I install the cogito-mem (Cogi) MCP server?

cogito-mem (Cogi) runs locally as a PyPI package, launched with uvx cogito-mem. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

pypi · cogito-mem

# add to Claude Code
claude mcp add meridian21lab-cogito-mem -- uvx cogito-mem
Common questions

What is the cogito-mem (Cogi) MCP server?

cogito-mem (Cogi) is an MCP server listed in the public MCP registry as io.github.meridian21lab/cogito-mem. Local long-term memory for Claude Code and other agents: every message kept word for word, no cloud. This page covers its PyPI package (cogito-mem).

Is the cogito-mem (Cogi) MCP server safe to use?

cogito-mem (Cogi) scores 81 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 22 October 2026. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the cogito-mem (Cogi) MCP server expose?

cogito-mem (Cogi) exposes 2 tools: memory_append, memory_query. Their descriptions and schemas cost roughly 323 tokens of context every time the server is loaded.

Is the cogito-mem (Cogi) MCP server still maintained?

cogito-mem (Cogi) is still listed as active in the MCP registry. We last reached this channel on 22 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the cogito-mem (Cogi) MCP server under?

cogito-mem (Cogi) declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.