# Knowledge Forest (mcpb · knowledge-forest-mcp.mcpb)

Local-first personal knowledge and learning memory for AI tutors with evidence-gated mastery.

- Trust score: 58/100 (low)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-17

## Components

- mcpb · `knowledge-forest-mcp.mcpb`: 58/100 (this document), [markdown](https://verifymcp.io/servers/znecho9-knowledge-forest-mcp/https-github-com-znecho9-knowledge-forest-mcp-releases-download-v0-1-1-knowledge.md), [page](https://verifymcp.io/servers/znecho9-knowledge-forest-mcp/https-github-com-znecho9-knowledge-forest-mcp-releases-download-v0-1-1-knowledge)

## Channel facts

- Registry: `mcpb`
- Package: `https://github.com/znecho9/knowledge-forest-mcp/releases/download/v0.1.1/knowledge-forest-mcp.mcpb`
- 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 2026-10-17.

- **Supply Chain Security**: 25/100
  - No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.
  - Known CVEs were checked across the 3 of 3 dependencies we could resolve, so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - 0 of 3 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 48/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (Apache-2.0).
  - Actively maintained (last published 22 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 80/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 665 tokens (~66/item across 10 items; 10 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 77/100
  - Stability observed for 23 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 68/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 4% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 10 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 11 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the Knowledge Forest MCP server?

Knowledge Forest ships as an MCPB bundle, a single file you download and open in an MCP host that supports MCPB bundles, such as Claude Desktop. The host reads the launch command from the bundle's own manifest, so there is no command to copy. The MCP registry declares no SHA-256 for this bundle, so there is no published digest to check the download against.

- Download bundle: `https://github.com/znecho9/knowledge-forest-mcp/releases/download/v0.1.1/knowledge-forest-mcp.mcpb`

## 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.

### 2026-10-17 (score 58, +1)

No change was recorded against any check on this day. Stability & Change Management went from 73 to 77. That category is still filling its 30-day observation window: 22 days of observed history at the previous scan, 23 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-15 (score 57, +1)

No change was recorded against any check on this day. Stability & Change Management went from 67 to 70. That category is still filling its 30-day observation window: 20 days of observed history at the previous scan, 21 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-13 (score 56, +1)

No change was recorded against any check on this day. Stability & Change Management went from 60 to 63. That category is still filling its 30-day observation window: 18 days of observed history at the previous scan, 19 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-12 (score 55, +1)

No change was recorded against any check on this day. Stability & Change Management went from 53 to 60. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-10 (score 54, +2)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 53. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-04 (score 52, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-02 (score 51, +4)

- [functional improvement] Stability: unverified → 0.27

### 2026-09-28 (score 47, 0)

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

## MCP tools (10)

### `forest_overview` (~47 tokens)

View knowledge forest overview

Read goals, mastery counts, and the next ready knowledge nodes. Call this first; it never modifies learning state.

Input parameters:

- `goal_id` (string): Optional goal ID to scope the overview.

### `search_knowledge` (~41 tokens)

Search knowledge nodes

Search canonical nodes before creating a goal tree. Results include reuse context and current mastery state.

Input parameters:

- `limit` (integer)
- `query` (string, required)

### `get_node_context` (~41 tokens)

Get complete node context

Read a knowledge node, its goal memberships, prerequisites, dependents, learning entries, verification history, and deterministic diagnosis.

Input parameters:

- `node_id` (string, required)

### `create_goal_tree` (~51 tokens)

Create a minimal sufficient goal tree

Persist one observable goal, its branches, and prerequisite-linked knowledge nodes. Search first. Use reuse_node_id only for truly equivalent existing concepts.

Input parameters:

- `branches` (array, required)
- `goal` (object, required)

### `update_node_learning_state` (~65 tokens)

Update learning depth or workflow state

Set a learner-selected depth or non-verified workflow state. This tool cannot mark mastery; use record_verification for that.

Input parameters:

- `desired_depth` (string)
- `node_id` (string, required)
- `reason` (string, required)
- `status` (string)

### `append_learning_note` (~68 tokens)

Append a learning record

Append a note, reflection, source, or exercise to a node. Source-visible material never changes mastery state.

Input parameters:

- `content` (string, required)
- `kind` (string, required)
- `node_id` (string, required)
- `source_visibility` (string, required)
- `sources` (array)

### `record_verification` (~95 tokens)

Record closed-book mastery evidence

Record one verification attempt. Mastery advances only for demonstrated, novel, unassisted, closed-book performance; the server computes acceptance.

Input parameters:

- `assisted` (boolean, required)
- `closed_book` (boolean, required)
- `node_id` (string, required)
- `novel_prompt` (boolean, required)
- `outcome` (string, required)
- `prompt` (string, required)
- `rationale` (string, required)
- `response` (string, required)

### `get_learning_queue` (~38 tokens)

Get the actionable learning queue

Return ready and prerequisite-blocked nodes, ordered by readiness and importance.

Input parameters:

- `goal_id` (string)
- `limit` (integer)

### `diagnose_node` (~41 tokens)

Diagnose a knowledge node

Deterministically identify prerequisite, depth, and evidence gaps and recommend the next learning action. It does not call a model.

Input parameters:

- `node_id` (string, required)

### `export_forest` (~24 tokens)

Export the complete forest

Read the complete portable forest state, including append-only learning records and evidence.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/znecho9-knowledge-forest-mcp/https-github-com-znecho9-knowledge-forest-mcp-releases-download-v0-1-1-knowledge#diagnostics

## Score history

- 2026-10-17: 58
- 2026-10-16: 57
- 2026-10-15: 57
- 2026-10-14: 56
- 2026-10-13: 56
- 2026-10-12: 55
- 2026-10-10: 54
- 2026-10-04: 52
- 2026-10-03: 51
- 2026-10-02: 51
- 2026-10-01: 47
- 2026-09-30: 47
- 2026-09-29: 47
- 2026-09-28: 47
- 2026-09-27: 47
- 2026-09-26: 47
- 2026-09-25: 47
- 2026-09-24: 47

## Common questions

### What is the Knowledge Forest MCP server?

Knowledge Forest is an MCP server listed in the public MCP registry as io.github.znecho9/knowledge-forest-mcp. Local-first personal knowledge and learning memory for AI tutors with evidence-gated mastery. This page covers its MCPB bundle (https://github.com/znecho9/knowledge-forest-mcp/releases/download/v0.1.1/knowledge-forest-mcp.mcpb).

### Is the Knowledge Forest MCP server safe to use?

Knowledge Forest scores 58 out of 100 on VerifyMCP. It declares no install or post-install scripts. 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 Knowledge Forest MCP server expose?

Knowledge Forest exposes 10 tools: forest_overview, search_knowledge, get_node_context, create_goal_tree, update_node_learning_state, and 5 more. Their descriptions and schemas cost roughly 511 tokens of context every time the server is loaded.

### What licence is the Knowledge Forest MCP server under?

Knowledge Forest declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- Repository: https://github.com/znecho9/knowledge-forest-mcp
- Changelog RSS feed: https://verifymcp.io/servers/znecho9-knowledge-forest-mcp/https-github-com-znecho9-knowledge-forest-mcp-releases-download-v0-1-1-knowledge.xml
- Changelog JSON feed: https://verifymcp.io/servers/znecho9-knowledge-forest-mcp/https-github-com-znecho9-knowledge-forest-mcp-releases-download-v0-1-1-knowledge.json
- HTML version of this page: https://verifymcp.io/servers/znecho9-knowledge-forest-mcp/https-github-com-znecho9-knowledge-forest-mcp-releases-download-v0-1-1-knowledge