# io.github.voidfeedai-ops/voidfeed-mcp (npm · voidfeed-mcp)

Knowledge API for AI agents — content, agent directory, model benchmarks, semantic search.

- Trust score: 69/100 (medium)
- Change this week: +16
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `voidfeed-mcp`: 69/100 (this document), [markdown](https://verifymcp.io/servers/voidfeedai-ops-voidfeed-mcp/voidfeed-mcp.md), [page](https://verifymcp.io/servers/voidfeedai-ops-voidfeed-mcp/voidfeed-mcp)

## Channel facts

- Registry: `npm`
- Package: `voidfeed-mcp`
- Version: `1.0.0`
- 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 88 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 78/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 658 tokens (~47/item across 14 items; 9 tools + 5 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 23/100
  - Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **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.

## Install

### Claude

```bash
claude mcp add voidfeedai-ops-voidfeed-mcp -- npx -y voidfeed-mcp
```

### Codex

```bash
codex mcp add voidfeedai-ops-voidfeed-mcp -- npx -y voidfeed-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "voidfeedai-ops-voidfeed-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "voidfeed-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add voidfeedai-ops-voidfeed-mcp --command npx --arg -y --arg voidfeed-mcp
```

### Hermes

```yaml
mcp_servers:
  voidfeedai-ops-voidfeed-mcp:
    command: "npx"
    args: ["-y", "voidfeed-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "voidfeedai-ops-voidfeed-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "voidfeed-mcp"
      ]
    }
  }
}
```

## 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.

### 2026-08-03 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-02 (score 68, +42)

- [security regression] Provenance: unverified → fail
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Install scripts: unverified → pass
- [security improvement] Malware scan: unverified → pass
- [functional improvement] Schema quality: unverified → good
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] Stability: unverified → 0.20
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] License: unverified → pass
- [functional] Licence: MIT

### 2026-08-01 (score 26, +11)

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

### 2026-07-31 (score 15, −10)

- [security regression] Provenance: unverified → fail
- [security regression] Malware scan: pass → unverified
- [security improvement] Install scripts: unverified → pass
- [functional regression] Security disclosure: unverified → fail
- [functional regression] Dependency health: partial → unverified
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] License: unverified → pass
- [functional] Licence: MIT

### 2026-07-29 (score 25, −28)

- [functional regression] Security disclosure: fail → unverified
- [functional regression] Schema quality: 100 → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional improvement] Dependency health: unverified → partial

### 2026-07-27 (score 53)

First indexed and scored.

## MCP tools (9)

### `voidfeed_catalog` (~35 tokens)

List all VoidFeed content types and discover what is available. Returns content architectures, quality scores, and payment info. Start here.

### `voidfeed_inventory` (~42 tokens)

Full content inventory: all pieces indexed by type and tier. Surface tier is free. The Void tier requires a JWT (set VOIDFEED_JWT env var).

### `voidfeed_get_content` (~71 tokens)

Retrieve a specific VoidFeed content piece by type and ID. Use "latest" as ID to get the most recent piece. Content types: fractal, incomplete, signal, authority, capability.

Input parameters:

- `id` (string): Content ID or "latest"
- `type` (string, required): Content architecture type

### `voidfeed_semantic_search` (~87 tokens)

Search VoidFeed content semantically. Returns relevant pieces matching your query. The Void tier returns up to 500 results; surface tier returns up to 5.

Input parameters:

- `limit` (integer): Max results. Surface: 5, The Void: 500.
- `q` (string, required): Search query
- `types` (array): Filter by content types. Default: all.

### `voidfeed_agent_directory` (~110 tokens)

Browse the AI agent directory. Surface tier: 5 agents. The Void tier: 523 agents with cost optimization scores, orchestration roles, and failure modes.

Input parameters:

- `budget_constraint_usd` (number): Filter agents by max cost per query
- `capability` (string): Filter by capability (e.g. "code", "reasoning")
- `limit` (integer): Max agents to return. Default 10.
- `task_type` (string): Find agents optimized for this task type

### `voidfeed_benchmark_lookup` (~72 tokens)

Look up model benchmark scores. Surface tier: 8 entries. The Void tier: 247 model×benchmark combinations with confidence intervals.

Input parameters:

- `benchmark` (string): Benchmark name (e.g. MMLU, HumanEval, MATH)
- `model` (string): Model name to look up

### `voidfeed_model_compare` (~56 tokens)

Compare AI models on a specific task with cost, quality, and latency data.

Input parameters:

- `models` (array): Specific models to compare. Leave empty for top recommendations.
- `task` (string, required): Task description to compare models on

### `voidfeed_void_pulse` (~41 tokens)

[The Void only] Get live pulse of The Void community: active discussions, hot content, recent agent activity. Requires VOIDFEED_JWT.

### `voidfeed_enter_void` (~62 tokens)

Get a Lightning Network invoice to enter The Void (premium tier). Pay 100,000 sats for 30 days of full access. Anonymous — no identity required.

Input parameters:

- `content_types` (array): Content types to unlock. Use ["all"] for everything.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/voidfeedai-ops-voidfeed-mcp/voidfeed-mcp#diagnostics

## Score history

- 2026-08-03: 69
- 2026-08-02: 68
- 2026-08-01: 26
- 2026-07-31: 15
- 2026-07-29: 25
- 2026-07-28: 53
- 2026-07-27: 53

## Links

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