# io.github.sumanaddanki/suma-memory (npm · suma-mcp-proxy)

Persistent memory for Claude Code and Cursor. Stop re-explaining your project every session.

- Trust score: 61/100 (medium)
- Change this week: +17
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `sumapro.quadframe.work`: 23/100, [markdown](https://verifymcp.io/servers/sumanaddanki-suma-memory/sumapro.md), [page](https://verifymcp.io/servers/sumanaddanki-suma-memory/sumapro)
- npm · `suma-mcp-proxy`: 61/100 (this document), [markdown](https://verifymcp.io/servers/sumanaddanki-suma-memory/suma-mcp-proxy.md), [page](https://verifymcp.io/servers/sumanaddanki-suma-memory/suma-mcp-proxy)

## Channel facts

- Registry: `npm`
- Package: `suma-mcp-proxy`
- Version: `1.4.0`
- 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**: 86/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (94 of 98), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (94 of 98), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 107 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 55/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1141 tokens (~163/item across 7 items; 7 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **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.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 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

### Claude

```bash
claude mcp add sumanaddanki-suma-memory -- npx -y suma-mcp-proxy
```

### Codex

```bash
codex mcp add sumanaddanki-suma-memory -- npx -y suma-mcp-proxy
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "sumanaddanki-suma-memory": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "suma-mcp-proxy"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add sumanaddanki-suma-memory --command npx --arg -y --arg suma-mcp-proxy
```

### Hermes

```yaml
mcp_servers:
  sumanaddanki-suma-memory:
    command: "npx"
    args: ["-y", "suma-mcp-proxy"]
```

### Other

```json
{
  "mcpServers": {
    "sumanaddanki-suma-memory": {
      "command": "npx",
      "args": [
        "-y",
        "suma-mcp-proxy"
      ]
    }
  }
}
```

## 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.

### 2026-08-02 (score 61, +42)

- [security regression] Provenance: unverified → fail
- [security improvement] Install scripts: unverified → pass
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Malware scan: unverified → pass
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional regression] Security disclosure: fail → unverified
- [functional improvement] License: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Schema quality: unverified → good
- [functional] Licence: MIT

### 2026-07-31 (score 19, −25)

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

### 2026-07-27 (score 44)

First indexed and scored.

## MCP tools (7)

### `suma_ping` (~22 tokens)

Health check — verify connection and org. Call once at session start.

### `suma_ingest` (~531 tokens)

Add knowledge to the SUMA graph.

The engine accepts any form of input — raw conversational paragraphs, verbatim file
excerpts, synthesized factual statements, or compressed semantic summaries. K-WIL
gravity (cosine² × decay × harmonic_weight) will rank all nodes correctly regardless
of ingestion style. How you drive the engine is determined by your use case, not the
engine itself.

Provenance tip: always populate source_doc and source_page so retrieved nodes can be
traced back to the physical file. The engine stores provenance but does not enforce it.

Args:
  text: The compressed knowledge to store (required)
  sphere: Category - family, work, friends, health, architecture (optional, auto-classified)
  extract_relationships: Auto-extract entities (default: true)
  source_doc: Where this came from — file path, URL, or document title (optional)
  source_section: Chapter, heading, or function name within the document (optional)
  source_page: Page number (PDF) or line number (code) (optional)
  source_type: 'manual'|'file'|'pdf'|'url'|'code' (optional, default: manual)

Response fields:
  node_id: ID of the created or reinforced node
  status: 'created' | 'merged' (merged = near-duplicate detected by Gate 2)
  similarity: Cosine similarity score against the nearest existing node (0.0–1.0). Only present when status='merged'.
  harmonic_weight: Updated harmonic weight of the node after Gate 2 Hebbian reinforcement. Near-duplicates strengthen the existing node instead of creating noise.
  reinforcement: How much harmonic_weight increased this ingest (e.g. 0.05–0.20). Higher for near-identical content. Only present when status='merged'.

Input parameters:

- `extract_relationships` (boolean): Extract entities (default: true)
- `label` (string): Short human-readable title for this node — shown in results, NOT searched (e.g. 'Patent Claim #3', 'Chapter 5 intro')
- `source_doc` (string): File path, URL, or document title this came from
- `source_page` (integer): Page number (PDF) or line number (code)
- `source_section` (string): Chapter, heading, or function name within the doc
- `source_type` (string): Source type (default: manual)
- `sphere` (string): Category (auto-classified if omitted)
- `text` (string, required): The knowledge to store

### `suma_search` (~244 tokens)

Search the knowledge graph using Gravity Well Algorithm.

Phases:
  1\. Entity Strike — find entity by name
  2\. Neighborhood Expansion — get relationships
  3\. Evidence Bridge — get related nodes
  4\. GIN Fallback — full-text search

Args:
  query: Natural language query (required)
  limit: Max results (default: 10)
  sphere: Filter by one sphere, OR pass an array for multi-sphere queries (optional)
          e.g. "work" or ["work", "personal"]
  historical_search: Set true ONLY when user explicitly asks for past events, older data,
                     or specific date ranges ("last year", "in 2024", "back in March",
                     "what did I do previously"). Suppresses time decay so old nodes
                     surface correctly. Defaults to false.

Input parameters:

- `historical_search` (boolean): Suppress time decay for explicit historical queries (default: false)
- `limit` (integer): Max results (default: 10)
- `query` (string, required): Natural language query
- `sphere`: Filter by sphere(s) — string or array of strings

### `suma_talk` (~98 tokens)

Bidirectional memory — search AND learn in one call.

Searches for relevant context, optionally stores the message as new knowledge.

Args:
  message: User message (required)
  learn: Store message as knowledge (default: true)
  sphere: Category for storage (optional)

Input parameters:

- `learn` (boolean): Store as knowledge (default: true)
- `message` (string, required): User message
- `sphere` (string): Category for storage

### `suma_correct` (~122 tokens)

Correct an incorrect node — preserves audit trail, cleans graph.

The node is marked as superseded (never deleted), and all its mentions/entities are cleaned.
Use this when you find incorrect information in the knowledge graph.

Args:
  node_id: The node ID to correct (required)
  reason: Why this node is wrong (required)
  replacement_text: Correct information to ingest (optional)

Input parameters:

- `node_id` (string, required): Node ID to correct
- `reason` (string, required): Why this is wrong
- `replacement_text` (string): Correct information (optional)

### `suma_stats` (~75 tokens)

Graph statistics and K-WIL token economics for this org.

Returns node count, sphere breakdown, queries used, tokens sent vs baseline,
compression ratio, and estimated cost saved. The ROI receipt — call this to
show the user how much context window budget SUMA has saved them.

No arguments needed — reads from the authenticated org.

### `suma_clean` (~49 tokens)

Wipe all data for this org. DESTRUCTIVE — requires confirmation.

Args:
  confirm: Must be true to proceed (required)

Input parameters:

- `confirm` (boolean, required): Must be true to wipe data

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/sumanaddanki-suma-memory/suma-mcp-proxy#diagnostics

## Score history

- 2026-08-03: 61
- 2026-08-02: 61
- 2026-08-01: 19
- 2026-07-31: 19
- 2026-07-30: 44
- 2026-07-28: 44
- 2026-07-27: 44

## Links

- npm package: https://www.npmjs.com/package/suma-mcp-proxy
- Socket report: https://socket.dev/npm/package/suma-mcp-proxy
- Repository: https://github.com/sumanaddanki/suma-mcp
- Changelog RSS feed: https://verifymcp.io/servers/sumanaddanki-suma-memory/suma-mcp-proxy/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/sumanaddanki-suma-memory/suma-mcp-proxy/changelog.json
- HTML version of this page: https://verifymcp.io/servers/sumanaddanki-suma-memory/suma-mcp-proxy