# Octobrain (mcpb · octobrain-0.15.1-x86_64-unknown-linux-musl.mcpb)

Persistent memory for AI assistants with semantic search and knowledge graph relationships.

- Trust score: 49/100 (low)
- Change this week: 0
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-04

## Components

- mcpb · `octobrain-0.15.1-aarch64-apple-darwin.mcpb`: 6/100, [markdown](https://verifymcp.io/servers/muvon-octobrain/https-github-com-muvon-octobrain-releases-download-0-14-3-octobrain-0-14-3-aarch.md), [page](https://verifymcp.io/servers/muvon-octobrain/https-github-com-muvon-octobrain-releases-download-0-14-3-octobrain-0-14-3-aarch)
- mcpb · `octobrain-0.15.1-aarch64-pc-windows-msvc.mcpb`: 5/100, [markdown](https://verifymcp.io/servers/muvon-octobrain/https-github-com-muvon-octobrain-releases-download-0-14-3-octobrain-0-14-3-aarch-2.md), [page](https://verifymcp.io/servers/muvon-octobrain/https-github-com-muvon-octobrain-releases-download-0-14-3-octobrain-0-14-3-aarch-2)
- mcpb · `octobrain-0.15.1-aarch64-unknown-linux-musl.mcpb`: 6/100, [markdown](https://verifymcp.io/servers/muvon-octobrain/https-github-com-muvon-octobrain-releases-download-0-14-3-octobrain-0-14-3-aarch-3.md), [page](https://verifymcp.io/servers/muvon-octobrain/https-github-com-muvon-octobrain-releases-download-0-14-3-octobrain-0-14-3-aarch-3)
- mcpb · `octobrain-0.15.1-x86_64-pc-windows-msvc.mcpb`: 5/100, [markdown](https://verifymcp.io/servers/muvon-octobrain/https-github-com-muvon-octobrain-releases-download-0-14-3-octobrain-0-14-3-x86-6.md), [page](https://verifymcp.io/servers/muvon-octobrain/https-github-com-muvon-octobrain-releases-download-0-14-3-octobrain-0-14-3-x86-6)
- mcpb · `octobrain-0.15.1-x86_64-unknown-linux-musl.mcpb`: 49/100 (this document), [markdown](https://verifymcp.io/servers/muvon-octobrain/https-github-com-muvon-octobrain-releases-download-0-14-3-octobrain-0-14-3-x86-6-2.md), [page](https://verifymcp.io/servers/muvon-octobrain/https-github-com-muvon-octobrain-releases-download-0-14-3-octobrain-0-14-3-x86-6-2)
- npm · `@muvon/octobrain`: 39/100, [markdown](https://verifymcp.io/servers/muvon-octobrain/muvon-octobrain.md), [page](https://verifymcp.io/servers/muvon-octobrain/muvon-octobrain)

## Channel facts

- Registry: `mcpb`
- Package: `https://github.com/Muvon/octobrain/releases/download/0.15.1/octobrain-0.15.1-x86_64-unknown-linux-musl.mcpb`
- Transport: `stdio`
- SHA-256: `c8b8b42405e3b9eee15b8f9fe0bd9a8cd5258056513eef905d448b581b35417c`

## 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 2026-11-04.

- **Supply Chain Security**: 0/100
  - 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 could not be checked: we found no dependency list to check in this bundle: either it runs a compiled binary, whose bundled manifests we do not read, or none of the package.json, requirements.txt, pyproject.toml or uv.lock files it ships for its runtime declares a dependency we can read (a requirements.txt that only points at a setup.py project, a local path, or a nested requirements file we cannot follow counts as none).
  - Install-script risk not yet assessed.
  - Dependency health could not be checked: we found no dependency list to check in this bundle: either it runs a compiled binary, whose bundled manifests we do not read, or none of the package.json, requirements.txt, pyproject.toml or uv.lock files it ships for its runtime declares a dependency we can read (a requirements.txt that only points at a setup.py project, a local path, or a nested requirements file we cannot follow counts as none).
- **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: no license is declared.
  - Actively maintained (last published 1 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 59/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 2307 tokens (~576/item across 4 items; 4 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 100/100
  - No destabilizing schema changes in the last 30 days.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% 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 4 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 5 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).

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the Octobrain MCP server?

Octobrain 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. Before opening it, check the file's SHA-256 matches the one the MCP registry declares for it, c8b8b42405e3b9eee15b8f9fe0bd9a8cd5258056513eef905d448b581b35417c; the commands to do that are on this page. If it does not match, do not open it.

- Download bundle: `https://github.com/Muvon/octobrain/releases/download/0.15.1/octobrain-0.15.1-x86_64-unknown-linux-musl.mcpb`
- SHA-256: `c8b8b42405e3b9eee15b8f9fe0bd9a8cd5258056513eef905d448b581b35417c`

### Verify on macOS / Linux

```bash
echo "c8b8b42405e3b9eee15b8f9fe0bd9a8cd5258056513eef905d448b581b35417c  octobrain-0.15.1-x86_64-unknown-linux-musl.mcpb" | shasum -a 256 -c
```

### Verify on Windows (PowerShell)

```powershell
(Get-FileHash -Algorithm SHA256 .\octobrain-0.15.1-x86_64-unknown-linux-musl.mcpb).Hash -eq "c8b8b42405e3b9eee15b8f9fe0bd9a8cd5258056513eef905d448b581b35417c"
```

## 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.

### 2026-11-04 (score 49, 0)

- [security] Stability: 0.97 → pass

### 2026-11-03 (score 49, +1)

No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-02 (score 48, −1)

- [functional] Stability: pass → 0.93

### 2026-10-28 (score 49, 0)

- [functional regression] Schema quality: 457 → 576

### 2026-10-27 (score 49, 0)

- [security] Stability: 0.97 → pass

### 2026-10-26 (score 49, +1)

No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-24 (score 48, +1)

No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-22 (score 47, +1)

No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (4)

### `forget` (~215 tokens)

Permanently delete memories. Irreversible — requires confirm=true. Use memory_id for single deletion, or query+filters for bulk removal. memory_id deletes any memory remember returned, project or global; query deletes only in the given scope (omitted: the session's project), so a project query never deletes global memories. Don't forget memories just because they're old — importance decay handles that. Only delete when information is wrong; for a replaced fact, memorize the new one with supersedes instead.

Input parameters:

- `confirm` (boolean, required): Must be true — deletion is permanent
- `memory_id` (string): ID of memory to delete (from remember results)
- `memory_types` (array): Filter by memory types when using query
- `query` (string): Semantic query to find memories to delete (alternative to memory_id)
- `role` (string): Role filter for query deletion
- `scope` (string): Scope to delete in. Omit for the session's project.
- `tags` (array): Filter by tags when using query

### `knowledge` (~807 tokens)

Knowledge base with six commands. The 'source' parameter (when used) ALWAYS refers to a SINGLE FILE or URL — never a directory; passing a directory path is an error. URLs are fetched anonymously — public documentation and information pages only, never API endpoints that need credentials (GitHub Actions logs, private repos, etc. return 403; use the platform's own CLI for those). 'search': semantic search across indexed content — provide source (single URL or file) to auto-index on-the-fly, omit to search all indexed sources, knowledge boxes included. 'store': save raw text under a unique key (session-scoped scratch, auto-cleaned, never durable) — error if key exists, delete first to replace. 'delete': remove stored content by key. 'read': fetch and return the FULL text content of a single URL or file — use ONLY as a last resort when search results are insufficient; prefer 'search' for targeted retrieval. 'match': search indexed content by regex pattern (like grep) — returns matching lines only; prefer 'search' for semantic queries, use 'match' for exact string/regex patterns. 'sync': re-index knowledge boxes — run it after you create, edit or delete files under '<repo>/.box/'. Supported file types: .html, .txt, .md, .pdf, .docx.

Knowledge boxes are the durable, shared knowledge base: files under '<repo>/.box/' (one topic per Markdown file, grouped in folders such as rules/, guides/, decisions/; the root README.md is not indexed), plus boxes subscribed with the octobrain CLI. Box results show source 'box://<box_id>/<path>'; for this project's box the file is '<repo>/.box/<path>' — edit it with your file tools, then 'sync'. A box:// source in search or match narrows to that one file; never pass a .box/ file path as source (it indexes a duplicate). One fact or decision belongs in memorize, not a box file.

Input parameters:

- `command` (string, required): Command to execute: search, store, delete, read, match, sync
- `content` (string): [store] Raw text content to store and index (required for store)
- `key` (string): [store/delete] Unique identifier key for the content. Error if key already exists on store — delete first to replace.
- `pattern` (string): [match] Regex pattern to search for in indexed content (e.g., "error_code" or "timeout|retry")
- `query` (string): [search] What to search for, in natural language (required for search)
- `source` (string): [search] Source filter — a SINGLE URL or local FILE path to auto-index and search within, or a box:// source from earlier results to search one box file. MUST point to one specific file (e.g. /path/t…

### `memorize` (~733 tokens)

Store information, insights, or context in memory. Call remember first to avoid duplicates. Set source='user_confirmed' for user-stated facts (importance 0.8-1.0), 'agent_inferred' for AI conclusions (0.3-0.6). Skip transient state or things easily re-derived. For a longer reference document, write a knowledge box file instead (see the knowledge tool).

Use related_to[] to link the new memory to existing ones in the same call. Relationship types: related_to, depends_on, supersedes, similar, conflicts, implements, extends, achieves, closes.

Knowledge updates: when a new fact replaces or corrects an existing memory (a value changed, a decision was reversed), memorize the new fact with related_to=[{target_id: <old_id>, relationship_type: 'supersedes'}]. Retrieval then ranks the current fact above the outdated one, which stays queryable for history. remember first to find the old_id.

Goal workflow:
1\. memorize a 'goal' type memory for the task — captures intent
2\. For each contributing memory: memorize with related_to=[{target_id: goal_id, relationship_type: 'achieves'}]
3\. When the task closes: memorize the completion / lesson-learned note with related_to=[{target_id: goal_id, relationship_type: 'closes'}] (goal_id must be a 'goal' memory with at least one Working achieves source). This triggers automatic consolidation — your closing memo becomes the consolidated parent, all Achieves sources transition to Consolidated state with dampened importance (still queryable for audit). Importance of the closing memo is bumped to max(sources) * 1.1. No separate consolidate call needed.

global=true (only available when session scope is locked): stores the memory in the shared global scope instead of the locked project scope. Use this for cross-project facts — user preferences, personal habits, universal conventions, tool choices — things that apply regardless of which project is active. Do NOT use global for project-specific knowledge.

Input parameters:

- `content` (string, required): Full content — explanations, code snippets, decisions, etc.
- `importance` (number): Importance 0.0-1.0: user facts 0.8-1.0, decisions 0.7-0.9, bug fixes 0.6-0.8, inferences 0.3-0.6
- `memory_type` (string): Memory category
- `related_files` (array): File paths related to this memory
- `related_to` (array): Optional: create typed relationships from this new memory to existing memories in the same call. Subsumes the standalone relate tool. Most common use: contributing toward a Goal via `{ target_id: goa…
- `role` (string): Role tag to attach to this memory (e.g. 'developer', 'reviewer').
- `scope` (string): Scope string to store this memory under (e.g. 'github.com/org/repo'). Omit for the session's project; without a session, omitted means global.
- `source` (string): Trust tier: 'user_confirmed' (user explicitly stated/approved) ranks higher in retrieval; 'agent_inferred' for AI conclusions
- `tags` (array): Tags for categorization and filtering
- `title` (string, required): Short descriptive title

### `remember` (~361 tokens)

Semantic search over stored memories. Call before memorize to avoid duplicates, and at task start to load context. Results include 1-hop graph neighbors automatically. A project scope also returns global memories. Prefer 2-5 related query terms for broader coverage. Results show [CONFIRMED]/[INFERRED] trust labels. For temporal questions ("last week", "in May"), set created_after/created_before (ISO-8601) to scope the time window — you know today's date, so compute the bounds.

Input parameters:

- `created_after` (string): Only return memories created on/after this time (ISO-8601, e.g. "2026-06-01" or "2026-06-01T00:00:00Z"). Use for temporal questions like "what did I decide last week".
- `created_before` (string): Only return memories created on/before this time (ISO-8601). Pair with created_after to scope a window (e.g. a specific month).
- `limit` (integer): Max memories to return
- `memory_types` (array): Narrow results to specific memory categories
- `min_relevance` (number): Minimum relevance score (0.0-1.0)
- `query` (required): String or array of 2-5 related terms (max 5; drop the weakest extras). Array preferred for broader semantic coverage.
- `related_files` (array): Filter by related file paths
- `role` (string): Filter by role. If omitted, returns memories for all roles.
- `scope` (string): Filter by scope. If omitted, returns memories from the session's project plus global ones (all scopes without a session).
- `tags` (array): Filter by tags

## Diagnostics

Captured diagnostic sections: Provenance. The full working is on the page: https://verifymcp.io/servers/muvon-octobrain/https-github-com-muvon-octobrain-releases-download-0-14-3-octobrain-0-14-3-x86-6-2#diagnostics

## Score history

- 2026-11-04: 49
- 2026-11-03: 49
- 2026-11-02: 48
- 2026-11-01: 49
- 2026-10-31: 49
- 2026-10-30: 49
- 2026-10-29: 49
- 2026-10-28: 49
- 2026-10-27: 49
- 2026-10-26: 49
- 2026-10-25: 48
- 2026-10-24: 48
- 2026-10-23: 47
- 2026-10-22: 47
- 2026-10-21: 46
- 2026-10-20: 46
- 2026-10-19: 45
- 2026-10-18: 45
- 2026-10-17: 44
- 2026-10-16: 44
- 2026-10-15: 43
- 2026-10-14: 43
- 2026-10-13: 42
- 2026-10-12: 41
- 2026-10-10: 41
- 2026-10-07: 40
- 2026-10-04: 35
- 2026-10-03: 35
- 2026-10-02: 35
- 2026-10-01: 35

## Common questions

### What is the Octobrain MCP server?

Octobrain is an MCP server listed in the public MCP registry as io.github.Muvon/octobrain. Persistent memory for AI assistants with semantic search and knowledge graph relationships. This page covers its MCPB bundle (https://github.com/Muvon/octobrain/releases/download/0.15.1/octobrain-0.15.1-x86_64-unknown-linux-musl.mcpb).

### Is the Octobrain MCP server safe to use?

Octobrain scores 49 out of 100 on VerifyMCP. 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 Octobrain MCP server expose?

Octobrain exposes 4 tools: forget, knowledge, memorize, remember. Their descriptions and schemas cost roughly 2,116 tokens of context every time the server is loaded.

## Links

- Repository: https://github.com/muvon/octobrain
- Changelog RSS feed: https://verifymcp.io/servers/muvon-octobrain/https-github-com-muvon-octobrain-releases-download-0-14-3-octobrain-0-14-3-x86-6-2.xml
- Changelog JSON feed: https://verifymcp.io/servers/muvon-octobrain/https-github-com-muvon-octobrain-releases-download-0-14-3-octobrain-0-14-3-x86-6-2.json
- HTML version of this page: https://verifymcp.io/servers/muvon-octobrain/https-github-com-muvon-octobrain-releases-download-0-14-3-octobrain-0-14-3-x86-6-2