# io.github.t-crew/memory-pulse (npm · memory-pulse)

Corrections that outlive the session. A guard blocks the edit that writes the old value back.

- Trust score: 86/100 (high trust)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

## Components

- npm · `memory-pulse`: 86/100 (this document), [markdown](https://verifymcp.io/servers/t-crew-memory-pulse/memory-pulse.md), [page](https://verifymcp.io/servers/t-crew-memory-pulse/memory-pulse)

## Channel facts

- Registry: `npm`
- Package: `memory-pulse`
- Version: `0.5.9`
- 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 2026-09-20.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - No production dependencies, so there is no dependency health to assess.
- **Provenance & Transparency**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to t-crew/memory-pulse).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 5 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 67/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 580 tokens (~145/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**: 70/100
  - Stability observed for 21 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 93/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 78% of tool parameters carry a description.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "execute" implies "execute" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 4 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### How do I install the io.github.t-crew/memory-pulse MCP server?

io.github.t-crew/memory-pulse runs locally as an npm package, launched with npx -y memory-pulse. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add t-crew-memory-pulse -- npx -y memory-pulse
```

### Cursor

```json
{
  "mcpServers": {
    "t-crew-memory-pulse": {
      "command": "npx",
      "args": [
        "-y",
        "memory-pulse"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "t-crew-memory-pulse": {
      "command": "npx",
      "args": [
        "-y",
        "memory-pulse"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add t-crew-memory-pulse -- npx -y memory-pulse
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add t-crew-memory-pulse --command npx --arg -y --arg memory-pulse
```

### Hermes

```yaml
mcp_servers:
  t-crew-memory-pulse:
    command: "npx"
    args: ["-y", "memory-pulse"]
```

### Netclaw

```json
{
  "McpServers": {
    "t-crew-memory-pulse": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "memory-pulse"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add t-crew-memory-pulse -t stdio -c npx -a -y memory-pulse
```

### Other

```json
{
  "mcpServers": {
    "t-crew-memory-pulse": {
      "command": "npx",
      "args": [
        "-y",
        "memory-pulse"
      ]
    }
  }
}
```

## 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.

### 2026-09-20 (score 86, +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.

### 2026-09-18 (score 85, +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.

### 2026-09-16 (score 84, +1)

No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-15 (score 83, +26)

- [security improvement] Malware scan: unverified → pass
- [security improvement] Known CVEs: unverified → pass
- [functional improvement] Dependency health: unverified → pass

### 2026-09-14 (score 57, −25)

- [security regression] Malware scan: pass → unverified
- [security regression] Known CVEs: pass → unverified
- [functional regression] Dependency health: pass → unverified
- [functional] Package version: 0.5.8 → 0.5.9

### 2026-09-12 (score 82, +1)

No change was recorded against any check on this day. Stability & Change Management went from 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-10 (score 81, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-09 (score 80, +15)

- [security improvement] Malware scan: unverified → pass

## MCP tools (4)

### `pulse` (~125 tokens)

Re-enter a project without reading its history into context. Returns a salience-ranked brief that ALWAYS carries every recorded correction first, so a superseded number cannot be quoted by accident. Call this before answering questions about prior work.

Input parameters:

- `budget` (number): Tokens you can spare for the brief. The brief is sized to fit; corrections always come first and whole.
- `root` (string): Entity to centre the causal front on.
- `tier` (string): index (smallest) → full. Default brief; omit it with `budget` to get the richest tier that fits.

### `recall` (~122 tokens)

Query the causal graph: what an event caused (effects), what caused it (causes), a multi-hop chain (pulse), or when a link was strongest (when). Hits carry a confidence; `exact` lists the recorded links verbatim, so a weak read never hides a correction. Returns nothing rather than guessing.

Input parameters:

- `object` (string): Second entity — required by 'when', which scores an edge.
- `op` (string, required)
- `subject` (string, required): Entity to query.
- `topk` (number): Max hits. Default 5.

### `remember` (~234 tokens)

Record a finding so the next session starts with it. Use kind='correction' when a claim is withdrawn or a number is superseded — corrections are surfaced first at every tier and never decay. Cheap, idempotent, and fully local (works offline).

Input parameters:

- `cause` (string, required)
- `effect` (string, required)
- `kind` (string): Default event.
- `note` (string): What was measured, and how.
- `pinned` (boolean): Never decays out of the brief.
- `replacement` (array): For corrections: the corrected value(s). An edit containing both a withdrawn term and a replacement (a comparison or disavowal) is allowed through the guard.
- `scope` (string): agent = the agent's own cross-project ledger (agent mode).
- `supersedes` (array): For corrections: ledger t values of earlier corrections whose withdrawn terms no longer bind.
- `tags` (array)
- `withdrawn` (array): For corrections: the exact strings that were withdrawn (a number, a name, a claim). The guard hook blocks an edit that writes them back.

### `execute` (~99 tokens)

Run a JavaScript program against memory in a sandbox; ONLY its return value enters context. Use for questions needing many lookups — filtering, counting, cross-referencing — where the intermediates would otherwise cost more than the answer. `ctx.memory.effects|causes|pulse|when` are available and async. Example: return (await ctx.memory.effects('x')).hits.length

Input parameters:

- `program` (string, required): Body of an async function; must return.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/t-crew-memory-pulse/memory-pulse#diagnostics

## Score history

- 2026-09-20: 86
- 2026-09-19: 85
- 2026-09-18: 85
- 2026-09-17: 84
- 2026-09-16: 84
- 2026-09-15: 83
- 2026-09-14: 57
- 2026-09-13: 82
- 2026-09-12: 82
- 2026-09-11: 81
- 2026-09-10: 81
- 2026-09-09: 80
- 2026-09-08: 65
- 2026-09-07: 53
- 2026-09-06: 53
- 2026-09-05: 79
- 2026-09-04: 78
- 2026-09-03: 67
- 2026-09-02: 67
- 2026-09-01: 66
- 2026-08-31: 66
- 2026-08-30: 51

## Common questions

### What is the io.github.t-crew/memory-pulse MCP server?

io.github.t-crew/memory-pulse is an MCP server listed in the public MCP registry as io.github.t-crew/memory-pulse. Corrections that outlive the session. A guard blocks the edit that writes the old value back. This page covers its npm package (memory-pulse).

### Is the io.github.t-crew/memory-pulse MCP server safe to use?

io.github.t-crew/memory-pulse scores 86 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 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 io.github.t-crew/memory-pulse MCP server expose?

io.github.t-crew/memory-pulse exposes 4 tools: pulse, recall, remember, execute. Their descriptions and schemas cost roughly 580 tokens of context every time the server is loaded.

### Is the io.github.t-crew/memory-pulse MCP server still maintained?

io.github.t-crew/memory-pulse is still listed as active in the MCP registry. We last reached this channel on 20 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 io.github.t-crew/memory-pulse MCP server under?

io.github.t-crew/memory-pulse declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/memory-pulse
- Socket report: https://socket.dev/npm/package/memory-pulse
- Repository: https://github.com/t-crew/memory-pulse
- Changelog RSS feed: https://verifymcp.io/servers/t-crew-memory-pulse/memory-pulse.xml
- Changelog JSON feed: https://verifymcp.io/servers/t-crew-memory-pulse/memory-pulse.json
- HTML version of this page: https://verifymcp.io/servers/t-crew-memory-pulse/memory-pulse