# com.kogcat/kogcat-mcp (pypi · kogcat-mcp)

Local-first judgment layer: counter-examples & blind spots from your own knowledge base.

- Trust score: 51/100 (low)
- Change this week: −20
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- pypi · `kogcat-mcp`: 51/100 (this document), [markdown](https://verifymcp.io/servers/com-kogcat-kogcat-mcp/kogcat-mcp.md), [page](https://verifymcp.io/servers/com-kogcat-kogcat-mcp/kogcat-mcp)

## Channel facts

- Registry: `pypi`
- Package: `kogcat-mcp`
- Version: `0.46.2`
- Transport: `stdio`

## Trust breakdown

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. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Supply Chain Security**: 50/100
  - Malware scan not yet available for this package.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs setuptools.build_meta at install time, a recognised native-build step with no shell scripting around it.
  - No production dependencies, so there is no dependency health to assess.
- **Provenance & Transparency**: 32/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - License check failed: the license (FSL-1.1-MIT) isn't a recognized OSI-approved license.
  - Actively maintained (last published 51 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 60/100
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 772 tokens (~85/item across 9 items; 9 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 84/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 53% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add com-kogcat-kogcat-mcp -- uvx kogcat-mcp
```

### Codex

```bash
codex mcp add com-kogcat-kogcat-mcp -- uvx kogcat-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-kogcat-kogcat-mcp": {
      "type": "local",
      "command": [
        "uvx",
        "kogcat-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-kogcat-kogcat-mcp --command uvx --arg kogcat-mcp
```

### Hermes

```yaml
mcp_servers:
  com-kogcat-kogcat-mcp:
    command: "uvx"
    args: ["kogcat-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "com-kogcat-kogcat-mcp": {
      "command": "uvx",
      "args": [
        "kogcat-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-03 (score 51, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-02 (score 50, +3)

- [functional improvement] Stability: unverified → 0.23

### 2026-07-31 (score 47, −24)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-27 (score 71, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-26 (score 71)

First indexed and scored.

## MCP tools (9)

### `search` (~110 tokens)

Similarity search over KB concepts. Returns hits with source_pack/stable_id.

Input parameters:

- `include_details` (boolean): Attach full node payload to each hit under `details`.
- `no_log` (boolean)
- `origin` (string)
- `scope` (string): 'mine' | '@owner/name' | 'all' (default)
- `text` (string, required): search query
- `top` (integer)
- `vertical` (string): R|W|M|all (default all)

### `node` (~61 tokens)

Fetch full node (concept/source/synthesis) by title or stable_id, including edges.

Input parameters:

- `scope` (string): 'mine' | '@owner/name'
- `stable_id` (string): UUID v4 — alternative to title
- `title` (string)

### `edges` (~48 tokens)

Graph traversal from a node. hops=1 or 2.

Input parameters:

- `hops` (integer)
- `scope` (string): 'mine' | '@owner/name'
- `title` (string, required)

### `calibrate` (~110 tokens)

KB calibration of an LLM draft. Returns {directive, debug?} where directive carries should_emit / placement / phrasing / inline_refs / user_facing_note / extras. Client renders directive verbatim — no internal stance/signal fields exposed. Read-only.

Input parameters:

- `client_id` (string)
- `source_kind` (string): Caller namespace (e.g. 'cc.parallel_query').
- `text` (string, required): LLM answer to calibrate against KB
- `top_k` (integer)

### `calibrate_review` (~220 tokens)

KB recall review of an LLM draft. Returns {review: {summary, has_signal, warnings[], clusters[], reinforce[]}}: warnings = opposition/invalidation signals (anchor + kind + note); clusters = anchor concepts each with structured cross-domain/contrast bridges (near/predicate/far/claim/cross_domain/tier); reinforce = supporting fallback (only when warnings + clusters both empty). Pass `question` (the focused question) + `seeds` (sub-queries / cross-language variants you expand the question into) to widen recall. Use for judgment / prediction / comparison questions. Read-only.

Input parameters:

- `client_id` (string)
- `question` (string): The focused user question (relevance frame for the anchor gate).
- `seeds` (array): Extra retrieval seeds: sub-queries / cross-language variants of the question.
- `source_kind` (string): Caller namespace (e.g. 'cc.parallel_query').
- `text` (string, required): LLM draft to review against KB
- `top_k` (integer)

### `memory_save` (~157 tokens)

Persist a user memory across sessions. Use source='user_explicit' when the user explicitly asks to remember; source='client_inferred' otherwise. type ∈ {user, feedback, project, reference}; type='lens' is the synthesized user-perspective profile (single canonical 'user_lens') — write it only via the memory-consolidate skill, never ad-hoc.

Input parameters:

- `body` (string): Markdown body (≤4KB utf-8).
- `description` (string, required): ≤200 chars; what this memory is about
- `name` (string, required): lowercase ascii identifier, [a-z][a-z0-9_]{0,79}
- `source` (string)
- `type` (string, required)

### `memory_delete` (~21 tokens)

Remove a memory by name.

Input parameters:

- `name` (string, required)

### `memory_list` (~18 tokens)

Return all memories' frontmatter (no body).

### `memory_get` (~27 tokens)

Fetch a single memory by name (frontmatter + body).

Input parameters:

- `name` (string, required)

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/com-kogcat-kogcat-mcp/kogcat-mcp#diagnostics

## Score history

- 2026-08-03: 51
- 2026-08-02: 50
- 2026-08-01: 47
- 2026-07-31: 47
- 2026-07-30: 71
- 2026-07-29: 71
- 2026-07-28: 71
- 2026-07-27: 71
- 2026-07-26: 71

## Links

- PyPI project: https://pypi.org/project/kogcat-mcp/
- Socket report: https://socket.dev/pypi/package/kogcat-mcp
- Repository: https://github.com/KogCat/cc-kogcat
- Changelog RSS feed: https://verifymcp.io/servers/com-kogcat-kogcat-mcp/kogcat-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-kogcat-kogcat-mcp/kogcat-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/com-kogcat-kogcat-mcp/kogcat-mcp