Memorix
NPM · MEMORIX · SCANNED SEP 21
Local-first project memory with legacy MCP and 2026 discovery compatibility.
Available components
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 Security89
- No malware found by supply-chain analysis.Pass
- CVE check failed: a known high-severity CVE affects sharp 0.33.5, reached via @lancedb/lancedb > @huggingface/transformers > sharp. A fixed version is available. View diagnostics → Fail
- No install/post-install scripts declared.Pass
- 103 of 308 dependencies flagged as unhealthy (2 deprecated). View diagnostics → Partial
Provenance & Transparency97
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to AVIDS2/memorix). View diagnostics → Pass
- Clear OSI-approved license (Apache-2.0).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 Usability63
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 2227 tokens (~247/item across 9 items; 9 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 Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage99
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 98% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 9 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 9 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
How do I install the Memorix MCP server?
Memorix runs locally as an npm package, launched with npx -y memorix. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · memorix
claude mcp add avids2-memorix -- npx -y memorix
{
"mcpServers": {
"avids2-memorix": {
"command": "npx",
"args": [
"-y",
"memorix"
]
}
}
} {
"servers": {
"avids2-memorix": {
"command": "npx",
"args": [
"-y",
"memorix"
]
}
}
} codex mcp add avids2-memorix -- npx -y memorix
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"avids2-memorix": {
"type": "local",
"command": [
"npx",
"-y",
"memorix"
],
"enabled": true
}
}
} openclaw mcp add avids2-memorix --command npx --arg -y --arg memorix
mcp_servers:
avids2-memorix:
command: "npx"
args: ["-y", "memorix"] {
"McpServers": {
"avids2-memorix": {
"Transport": "stdio",
"Command": "npx",
"Arguments": [
"-y",
"memorix"
]
}
}
} assistant mcp add avids2-memorix -t stdio -c npx -a -y memorix
{
"mcpServers": {
"avids2-memorix": {
"command": "npx",
"args": [
"-y",
"memorix"
]
}
}
} 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.
- 21 Sept 26 +8
- Known CVEs: unverified → fail ▼ security
- Stability: 0.97 → pass security
- Dependency health: unverified → 0.85 ▲ functional
- 20 Sept 26 −7
- Stability: 0.93 → unverified ▼ security
- Tool safety: pass → unverified ▼ security
- Known CVEs: fail → unverified ▼ security
- Capabilities: pass → unverified ▼ functional
- Dependency health: 0.85 → unverified ▼ functional
- Tool coverage: 100 → unverified ▼ functional
- Package version: 1.9.4 → 1.9.5 functional
- 19 Sept 26 −1
- Stability: pass → 0.93 functional
- 18 Sept 26 0
- Stability: pass → unverified ▼ security
- Tool safety: pass → unverified ▼ security
- Capabilities: pass → unverified ▼ functional
- Tool coverage: 100 → unverified ▼ functional
- Package version: 1.9.3 → 1.9.4 functional
- Package version: 1.4.2 → 1.9.4 functional
- 17 Sept 26 0
- Stability: 0.97 → pass security
- 16 Sept 26 0
- Stability: pass → 0.97 functional
- 15 Sept 26 +15
- Malware scan: unverified → pass ▲ security
- Stability: 0.97 → pass security
- 14 Sept 26 −15
- Malware scan: pass → unverified ▼ security
- Stability: pass → 0.97 functional
- Package version: 1.9.2 → 1.9.3 functional
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 21 Sept 2026 · Analysed npm/memorix@1.9.5
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 | npm |
| Reason | Verified |
| Discovered via | Registry attestation endpoint |
| Source repo | AVIDS2/memorix |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/AVIDS2/memorix/.github/workflows/publish.yml@refs/tags/v1.9.5 |
| Rekor log index | 2898183847 |
| Predicate type | https://slsa.dev/provenance/v1 |
| Subject digest | sha512:e8fa1d25de0d5c8368e5cca21d13dc03b483445496528a2839c1e76b49a4399e8f6b3e4cc7570bf49bc4716788f77101c6a81c3eacc77ca2e7fe579fd |
Background: How many MCP packages publish verified provenance →
Vulnerabilities 2 findings
| ID | CVE | Severity | Vector | Fix available |
|---|---|---|---|---|
| GHSA-f88m-g3jw-g9cj | high | yes | ||
| GHSA-rgj7-g3m4-5g8c | high | yes |
Background: What a vulnerability scan can and cannot prove →
Dependencies 308 packages
| Packages resolved | 308 |
|---|---|
| Deprecated | 2 |
| Stale | 101 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
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 →
memorix_codegraph_status CodeGraph Memory Status ~24
Show CodeGraph Memory provider and index status for the current project.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
memorix_context_pack Context Pack ~121
Build a prompt-ready working context pack for a coding task. Combines relevant memories, CodeGraph Memory facts, freshness warnings, suggested reads, and verification hints. After a complete memorix_project_context brief, provide purpose only when deliberately expanding beyond it.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Max active memories to inspect before code-ref filtering (default: 20) |
| purpose | string | – | Why this must expand beyond the latest Autopilot brief. Name the missing fact or the user's explicit request. |
| task | string | yes | Current coding task or question |
No output schema declared.
No examples provided.
memorix_detail Memory Details ~298
Fetch full observation, mini-skill, or curated durable-memory details — includes source kind (explicit memory / hook trace / git evidence), value category, and cross-references (~500-1000 tokens each). Do not re-fetch content already covered by a complete memorix_project_context brief unless a specific fact is still missing or the user asks for deeper history; provide purpose when intentionally expanding. Always use memorix_search first to find relevant IDs, then fetch only what you need. Accepts typed refs from search results (e.g. "obs:42", "skill:3") and durable refs from a project brief (e.g. "durable:<uuid>") via the typedRefs field, or legacy numeric ids / object refs for backward compatibility.
| Name | Type | Req | Description |
|---|---|---|---|
| force | boolean | – | Use only when the user explicitly asks to read a record already represented in the latest Autopilot brief. |
| ids | array | – | Observation IDs to fetch (legacy, from memorix_search results) |
| purpose | string | – | Why this must expand beyond the latest Autopilot brief. Name the missing fact or the user's explicit request. |
| refs | array | – | Explicit observation refs. Prefer this for global search results. |
| typedRefs | array | – | Typed memory refs from search results or a project brief, e.g. "obs:42", "skill:3", "durable:<uuid>", "obs:42@org/proj" |
No output schema declared.
No examples provided.
memorix_media Manage Controlled Media ~236
Use the controlled local media library for an explicit import, attachment, inspection, or MiniMax generation request. Assets stay outside the Git worktree and enter normal memory only when attach is explicitly true. Use the CLI for destructive removal, quota cleanup, and direct generation. MCP generation is disabled by default and requires MEMORIX_MCP_MEDIA_GENERATION=1 after the operator reviews provider billing.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | – |
| assetId | string | – | Controlled MediaAsset ID for attach/show. |
| attach | boolean | – | Attach generated/imported output to normal project memory explicitly. |
| jobId | string | – | Durable media job ID for status. |
| kind | string | – | Optional asset list filter. |
| limit | integer | – | Maximum assets to list. |
| maxChars | integer | – | Bounded PDF extraction character limit. |
| maxPages | integer | – | Bounded PDF extraction page limit. |
| narrative | string | – | Short retrieval text when attaching an asset. |
| path | string | – | Explicit local image/audio/video/PDF path for import. |
| title | string | – | Observation title when attaching generated/imported output. |
No output schema declared.
No examples provided.
memorix_project_context Memory Autopilot Project Context ~170
Build a compact Memory Autopilot brief for the current coding task. Schedules Code Memory refresh when needed, includes Start here files, reliable code-bound memories, stale/suspect cautions, and verification hints. Use this at the start of a new coding turn or after switching tasks.
| Name | Type | Req | Description |
|---|---|---|---|
| agent | string | – | Optional target agent for compatible workflow selection. |
| format | string | – | Output format. "prompt" is agent-ready; "summary" is human-readable; "receipt" is bounded JSON; "json" is detailed diagnostics. |
| limit | number | – | Reserved for future source limits; current prompt stays compact by default. |
| refresh | string | – | Code Memory refresh policy. auto refreshes only when missing or stale. |
| task | string | – | Current coding task or question |
No output schema declared.
No examples provided.
memorix_resolve Resolve Memories ~102
Mark observations as resolved (completed/no longer active). Resolved memories are hidden from default search but can still be found with status="all". Use this to mark completed tasks, fixed bugs, or outdated information so they don't pollute future context.
| Name | Type | Req | Description |
|---|---|---|---|
| ids | array | yes | Observation IDs to mark as resolved |
| status | string | – | Target status: "resolved" (default, completed/done) or "archived" (permanently hidden) |
No output schema declared.
No examples provided.
memorix_search Search Memory ~383
Search project memory. Returns a compact index (~50-100 tokens/result). Do not use as a follow-up to a complete memorix_project_context brief unless a specific fact is still missing or the user asks for deeper history; provide purpose when intentionally expanding. Use memorix_detail to fetch full content for specific IDs. Use memorix_timeline to see chronological context. Searches across all observations stored from any IDE session — enabling cross-session and cross-agent context retrieval.
| Name | Type | Req | Description |
|---|---|---|---|
| force | boolean | – | Use only when the user explicitly asks to read a record already represented in the latest Autopilot brief. |
| limit | number | – | Max results (default: 20) |
| maxTokens | number | – | Token budget — trim results to fit (0 = unlimited) |
| purpose | string | – | Why this must expand beyond the latest Autopilot brief. Name the missing fact or the user's explicit request. |
| quality | string | – | Retrieval profile: fast stays local, balanced uses configured embeddings, thorough explicitly permits optional LLM refinement. |
| query | string | yes | Search query (natural language or keywords) |
| scope | string | – | Search scope: "project" (default) only searches current project, "global" searches all projects |
| since | string | – | Only return observations created after this date (ISO 8601 or natural like "2025-01-15") |
| source | string | – | Filter by memory source. "git" returns only commit-derived ground truth memories. Omit for all sources. |
| status | string | – | Filter by memory status. "active" (default) shows current memories, "all" includes resolved/archived. |
| type | string | – | Filter by observation type |
| until | string | – | Only return observations created before this date (ISO 8601 or natural like "2025-02-01") |
No output schema declared.
No examples provided.
memorix_session_start Start Session ~384
Start a new coding session. Returns a compact continuation card with the latest handoff and a few memory references. Call this at the beginning of a session to track activity; retrieve a referenced memory only when it is relevant. Any previous active session for this project will be auto-closed. By default this is lightweight: it binds the project, opens a session, and avoids dumping full history into the new context. Coordination identity is opt-in via `joinTeam: true` or a separate `team_manage` join call. IMPORTANT for HTTP/control-plane mode: pass `projectRoot` with the absolute path to your workspace root (e.g., the directory open in your IDE). Memorix uses this to detect the git project and bind this session to the correct project context. Without it, project-scoped tools will be disabled.
| Name | Type | Req | Description |
|---|---|---|---|
| agent | string | – | Agent/IDE name (e.g., "cursor", "windsurf", "claude-code") |
| agentType | string | – | Agent type used for optional coordination identity mapping (e.g., "windsurf", "cursor"). |
| instanceId | string | – | Stable instance ID for optional coordination identity across restarts. If omitted with joinTeam=true, Memorix derives a deterministic fallback from the project and agent identity. |
| joinTeam | boolean | – | If true, also join orchestration coordination state for this session. Defaults to false. |
| projectRoot | string | – | Absolute path to the workspace/project root directory (e.g., the folder open in your IDE). Memorix will detect the git project from this path and bind this session to it. Required for HTTP transport… |
| role | string | – | Explicit role override used only when joinTeam=true. |
| sessionId | string | – | Custom session ID (auto-generated if omitted) |
No output schema declared.
No examples provided.
memorix_store Store Memory ~509
Store a new observation/memory. Automatically indexed for search. Use type to classify: gotcha ([GOTCHA] critical pitfall), decision ([DECISION] architecture choice), problem-solution ([FIX] bug fix), how-it-works ([INFO] explanation), what-changed ([CHANGE] change), discovery ([DISCOVERY] insight), why-it-exists ([WHY] rationale), trade-off ([TRADEOFF] compromise), session-request ([SESSION] original goal). Project visibility is the default. Personal or team visibility requires an explicitly joined coordination identity. Set longTerm only when the caller explicitly wants an additional source-backed long-term candidate; it is never injected until an operator records a review through the CLI. For a read-only task, do not store unless the user explicitly asks to save a record.
| Name | Type | Req | Description |
|---|---|---|---|
| attachments | array | – | Safe public provenance references. They are stored as metadata for lexical retrieval; raw inline media is never stored. |
| concepts | array | – | Related concepts/keywords |
| entityName | string | yes | The entity this observation belongs to (e.g., "auth-module", "port-config") |
| facts | array | – | Structured facts (e.g., "Default timeout: 60s") |
| filesModified | array | – | Files involved |
| longTerm | object | – | Optional explicit request to create a source-backed long-term candidate alongside this observation. Candidates are not automatically injected. |
| narrative | string | yes | Full description of the observation |
| overrideReadOnly | boolean | – | Use only when the user explicitly asks to save memory during a read-only or no-modification task. |
| progress | object | – | Progress tracking for task/feature observations |
| relatedCommits | array | – | Git commit hashes this memory relates to (links ground truth ↔ reasoning) |
| relatedEntities | array | – | Other entity names this memory cross-references |
| title | string | yes | Short descriptive title (~5-10 words) |
| topicKey | string | – | Optional topic identifier for upserts (e.g., "architecture/auth-model"). If an observation with the same topicKey already exists in this project, it will be UPDATED instead of creating a new one. Use… |
| type | string | yes | Observation type for classification |
| visibility | string | – | Retrieval scope. Project is the normal shared default; personal/team require memorix_session_start with joinTeam=true. |
No output schema declared.
No examples provided.
What is the Memorix MCP server?
Memorix is an MCP server listed in the public MCP registry as io.github.AVIDS2/memorix. Local-first project memory with legacy MCP and 2026 discovery compatibility. This page covers its npm package (memorix).
Is the Memorix MCP server safe to use?
Memorix scores 89 out of 100 on VerifyMCP. We recorded 2 known advisories against it as of 21 September 2026. It declares no install or post-install scripts. 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 Memorix MCP server expose?
Memorix exposes 9 tools: memorix_store, memorix_search, memorix_project_context, memorix_codegraph_status, memorix_context_pack, and 4 more. Their descriptions and schemas cost roughly 2,227 tokens of context every time the server is loaded.
Is the Memorix MCP server still maintained?
Memorix is still listed as active in the MCP registry. We last reached this channel on 21 September 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 Memorix MCP server under?
Memorix 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.