# PulseGate (remote · www.pulsegate.ai)

Bounded software search, unknown requirements, and the origins of project identifiers.

- Trust score: 85/100 (high trust)
- Change this week: +2
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `www.pulsegate.ai`: 85/100 (this document), [markdown](https://verifymcp.io/servers/ai-pulsegate-provenance/api-mcp.md), [page](https://verifymcp.io/servers/ai-pulsegate-provenance/api-mcp)

## Channel facts

- Endpoint: `https://www.pulsegate.ai/api/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.2.2`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, 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 2026-11-05.

- **Endpoint Security**: 80/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 69/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 598 tokens (~199/item across 3 items; 3 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 3 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - 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 PulseGate MCP server?

PulseGate is a hosted endpoint at https://www.pulsegate.ai/api/mcp, so there is nothing to install locally. 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 --transport http ai-pulsegate-provenance 'https://www.pulsegate.ai/api/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "ai-pulsegate-provenance": {
      "url": "https://www.pulsegate.ai/api/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ai-pulsegate-provenance": {
      "type": "http",
      "url": "https://www.pulsegate.ai/api/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.ai-pulsegate-provenance]
url = "https://www.pulsegate.ai/api/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ai-pulsegate-provenance": {
      "type": "remote",
      "url": "https://www.pulsegate.ai/api/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ai-pulsegate-provenance --url 'https://www.pulsegate.ai/api/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ai-pulsegate-provenance:
    url: "https://www.pulsegate.ai/api/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "ai-pulsegate-provenance": {
      "Transport": "http",
      "Url": "https://www.pulsegate.ai/api/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add ai-pulsegate-provenance -t streamable-http -u 'https://www.pulsegate.ai/api/mcp'
```

### Other

```json
{
  "mcpServers": {
    "ai-pulsegate-provenance": {
      "type": "http",
      "url": "https://www.pulsegate.ai/api/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## 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.

### 2026-11-01 (score 85, +1)

- [security] Stability: 0.97 → pass

### 2026-10-30 (score 84, +1)

No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-28 (score 83, +1)

No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-25 (score 82, +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.

### 2026-10-23 (score 81, +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.

### 2026-10-21 (score 80, +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.

### 2026-10-19 (score 79, +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.

### 2026-10-18 (score 78, +55)

- [security improvement] Authorization: unverified → partial
- [security improvement] Injection markers: unverified → pass
- [security improvement] HSTS header: fail → pass
- [security improvement] Transport: fail → pass
- [functional regression] MCP protocol: unverified → fail
- [functional improvement] Endpoint reachability: not serving MCP → reachable
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Stability: unverified → 0.53

## MCP tools (3)

### `search_catalog` (~233 tokens)

Find software for a task

Find software by name, task or recorded filters. Returns at most ten candidates from the same service as native HTML/HTTP search, with recordUrl and met/unmet/unknown requirement assessments. Unknown is not false. No complete profile, publisher fetch, bulk export or functionality guarantee.

Input parameters:

- `category` (string): Recorded category slug, including its descendants.
- `license` (string): Recorded license family, not a verified legal conclusion.
- `limit` (integer): Same normalization as HTTP search; at most ten combined identities.
- `page` (integer): Same normalization as HTTP search; depth beyond 50 is refused.
- `platform` (string): Recorded platform filter, using the HTTP search vocabulary.
- `pricing` (string): Recorded pricing classification, not proof of a price.
- `q` (string): Name or task; at most 512 UTF-8 bytes and 12 words. No model or translation is called.
- `require` (string): Up to three requirements, e.g. api:true,mcp:true. Missing or inferred evidence stays unknown.
- `unknown` (string): Defaults to include candidates needing verification.

### `lookup_project` (~127 tokens)

Read a project's identifier evidence

Return the external identifiers PulseGate holds for one project, and for each one how it arrived and whether anyone has checked that it belongs. Makes no claim about whether the software is alive, maintained, or working. Look up by slug, or by an identifier you already have.

Input parameters:

- `platform` (string): Identifier platform to look up by, e.g. "github_repo" or "npm_package". Use with value.
- `slug` (string): The PulseGate slug of the listing.
- `value` (string): The identifier on that platform, e.g. owner/name for github_repo.

### `list_identifier_platforms` (~42 tokens)

List supported identifier platforms

List every platform PulseGate records identifiers on, with how many identifiers it holds for each. Use it to learn the vocabulary the platform argument of lookup_project accepts.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/ai-pulsegate-provenance/api-mcp#diagnostics

## Score history

- 2026-11-05: 85
- 2026-11-04: 85
- 2026-11-03: 85
- 2026-11-02: 85
- 2026-11-01: 85
- 2026-10-31: 84
- 2026-10-30: 84
- 2026-10-29: 83
- 2026-10-28: 83
- 2026-10-27: 82
- 2026-10-26: 82
- 2026-10-25: 82
- 2026-10-24: 81
- 2026-10-23: 81
- 2026-10-22: 80
- 2026-10-21: 80
- 2026-10-20: 79
- 2026-10-19: 79
- 2026-10-18: 78
- 2026-10-17: 23
- 2026-10-16: 77
- 2026-10-15: 77
- 2026-10-14: 76
- 2026-10-13: 76
- 2026-10-12: 69
- 2026-10-11: 68
- 2026-10-10: 68
- 2026-10-05: 67
- 2026-10-04: 67
- 2026-10-03: 66

## Common questions

### What is the PulseGate MCP server?

PulseGate is an MCP server listed in the public MCP registry as ai.pulsegate/provenance. Bounded software search, unknown requirements, and the origins of project identifiers. This page covers its hosted endpoint (https://www.pulsegate.ai/api/mcp).

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

PulseGate scores 85 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 PulseGate MCP server expose?

PulseGate exposes 3 tools: search_catalog, lookup_project, list_identifier_platforms. Their descriptions and schemas cost roughly 402 tokens of context every time the server is loaded.

### Does the PulseGate MCP server require authentication?

No. We connected to PulseGate without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the PulseGate MCP server still maintained?

PulseGate is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://www.pulsegate.ai/api/mcp
- Website: https://www.pulsegate.ai/developers
- Changelog RSS feed: https://verifymcp.io/servers/ai-pulsegate-provenance/api-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-pulsegate-provenance/api-mcp.json
- HTML version of this page: https://verifymcp.io/servers/ai-pulsegate-provenance/api-mcp