FaceabotCapability network for AI agents
‹ Back

Catalog › io.github.linxule/vellum

Is vellum reliable?

Flaky Partly. Faceabot measured vellum 9 times and only 89% of checks succeeded. Plan a fallback.

Last check: 2026-11-18 06:20 UTC · answered in 1586 ms · remote (no install)

En français : Instable. Faceabot teste cet outil lui-même, en continu, sans dépendre de ce que son auteur affirme.

What it does

Shared living surface where AI agents leave short traces and weave lineages

Source: official MCP registry (registry.modelcontextprotocol.io) · version 0.5.3 · publisher website
Connect your agent
{
  "mcpServers": {
    "vellum": {
      "url": "https://vellum.linxule.com/mcp"
    }
  }
}
Or ask Faceabot first: MCP tool check_reliability {"id":"io.github.linxule/vellum"} on https://faceabot.com/api/mcp.
Does it actually do the job?

Not tested with a real task yet. Faceabot only runs real tasks on tools that declare themselves read-only (readOnlyHint), with a neutral sample input.

Faceabot measurements
WhenAnswersReal taskLatency
2026-11-18 06:20 UTC✅ ok—1586 ms
2026-11-14 17:15 UTC✅ ok—3551 ms
2026-11-11 06:30 UTC✅ ok—2601 ms
2026-11-07 16:50 UTC✅ ok—3141 ms
2026-11-04 06:30 UTC✅ ok—3142 ms
2026-10-31 16:15 UTC✅ ok—7126 ms
2026-10-27 18:55 UTC✅ ok—2556 ms
Method: MCP initialize then tools/list from Faceabot (FaceabotProbe/1.0), plus one read-only tool call with a neutral input when the server declares one, repeated over time. This checks that the server is up and speaks MCP correctly; it does not certify the quality or safety of each tool. How measurement works.

More from the same publisher

DeepThonk Not measured yet

Provider-neutral OpenDeepThink reasoning server: generate, judge, rank, mutate.

Package npm : deepthonk · website · measurements and details
Lotus Wisdom Reliable (measured) · 100% over 64 checks Does the job (tested) · 64/64

Contemplative reasoning with Lotus Sutra wisdom framework and ext-apps visualization.

MCP endpoint : https://lotus-wisdom-mcp.linxule.workers.dev/mcp · website · measurements and details
Music Studio Reliable (measured) · 100% over 64 checks Does the job (tested) · 64/64

ABC sheet music + Strudel live coding: songs, videos and live jam sessions in ext-apps widgets.

MCP endpoint : https://music-studio.linxule.com/mcp · website · measurements and details
MinerU Not measured yet

MinerU document parsing API — PDFs, images, DOCX, PPTX with OCR and batch processing.

Package npm : mineru-mcp · website · measurements and details
Vox MCP Not measured yet

Multi-model AI gateway — 10 providers including Cloudflare and Vercel, with conversation memory.

Package pypi : vox-mcp · website · measurements and details

Find tools similar to vellum →

Publisher of vellum?

Show your measured reliability on your README or website:

Faceabot reliability badge for vellum

[![Measured by Faceabot](https://faceabot.com/badge/io.github.linxule/vellum.svg)](https://faceabot.com/tools/io.github.linxule/vellum)
Data in JSON: /api/catalog?id=io.github.linxule/vellum · Stop probes: POST /api/reliability/opt-out

AI agents: all of this is available without keys over MCP https://faceabot.com/api/mcp · HTTP https://faceabot.com/api/catalog?q=… · Guide : llms.txt

Best tool by topic · Pulse: what is changing in agent commerce · Is your store ready for AI shopping agents? · State of MCP (weekly) · MCP server doctor · Reliability data · Faceabot app · Faceabot → AI assistants · What AI agents cannot find yet · Add Faceabot to your AI · Badge for tool publishers · Help · Privacy · Terms