MCP.Market

Skillfed MCP server

by skill-federation·io.github.skill-federation/skillfed-mcp·v0.1.3·15 stars
No reviews yet

Find vetted agent skills for your task — privacy-preserving skill discovery over MCP.

A91/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A91/100

full report

Adoption
Growing

15 stars48 downloads/wk

Reviews

Write one

Nobody has reviewed Skillfed yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Skillfed tools (4)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • emit_demand_pointer

    Record a missing capability on a MISS — a wish that returned zero candidates (empty), OR one

  • find_skills

    Search a federated catalog of vetted agent skills for a privacy-abstracted wish-list.

  • get_skill_bundle

    Fetch a confirmed match's bundle (SKILL.md + any extra files) for local install.

  • report_selection

    Report one wish's agentic-selection outcome. chosen = the selected skill id, or the literal

Public scan report

scanner v0.1.9 · 2026-09-26 · same rubric, same numbers if you re-run it

no findings
  • Code scan5 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 2 days ago15/15
  • Maintainer identityregistry namespace matches repository owner7/10
Overall 91/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Skillfed compares

Against every graded Productivity MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
91/100
higher than 85% of 1,299 Productivity servers
Tools
4
the typical Productivity server has 7
Tools that change things
0%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
15
more than 81% of 854 Productivity servers
Downloads a week
48
more than 37% of 427 Productivity servers with a package

What its tools let an agent do: 4 read

Install Skillfed in Claude Code, Cursor or VS Code

Runs npx -y skillfed-mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add skillfed-mcp -- npx -y skillfed-mcp
Add to Cursor

What the publisher says

From the Skillfed repository's README, as published. We do not edit it. Read it on GitHub

Skill Federation

Free, private skill search for AI agents

<!-- Row 1 — Traction & proof (emphasized: for-the-badge) -->

<!-- Row 2 — Install & run (compact: flat-square) --> -2E9E6B?style=flat-square)

<!-- Row 3 — Trust & terms (compact: flat-square) -->

Skills are hints, not installs. Your agent reads them as field notes; you approve the rare one worth keeping.

A bare agent solves 17.5% of SkillsBench tasks. With Skill Federation, 22.8% — and your work never leaves your machine.

Browse and search the indexed catalogs — skills, PyPI packages, research — on the web → skillfed.io

A model's weights are an average of what was written before its training cutoff, and a lossy one at that. Wherever practice actually moves — SEO, security review, accessibility, framework and API migrations, packaging and release, pricing, compliance, tooling defaults — that average is a confident summary of a past consensus. It reads exactly like expertise. It is also, quietly, a version or two behind.

A skill is not a script you install. It's a hint. Field notes a practitioner wrote down about how this work is currently done: a dated artifact someone maintains, carrying the difference between the average and the present. A frontier model pulls one into context and augments its weights with it. Nothing else happens. So the normal outcome of a search here is reading, not installing; a skill is reference material, not code that runs.

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Skillfed: common questions

Is Skillfed MCP server safe?
Yes, by our scan: it is graded A (91/100). Read the Skillfed safety report
How do I install Skillfed?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Skillfed need an API key?
No secret keys are declared. It reads 1 setting from the environment.
Is Skillfed maintained?
The last commit was 41 days ago (2026-09-24). The latest release is v0.1.3.
What can I use instead of Skillfed?
Servers from other publishers that do the same job: Mirroir MCP server, no_human MCP server and loci MCP server.
How does Skillfed compare with other Productivity MCP servers?
safety score 91/100 (higher than 85% of 1,299 Productivity servers); tools 4 (the typical Productivity server has 7); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Skillfed

Same job from other publishers: the closest match first, then the best rated.

  • Mirroir
    Drive a stock iPhone via iPhone Mirroring: no Developer Mode, Xcode or WDA. LLM-free skill replay.
    C
  • no_human
    File a task with your local no_human and check on it: task_add and task_status over stdio.
    B
  • loci
    Cross-session memory and hybrid RAG over your notes and docs. Local-first, with cited answers.
    A
  • GodPrompt MCP Server
    GodPrompt MCP + Agent Skill for coding agents with TDD, debugging, verification, and task routing.
    A
  • Agentpack
    Repo-native task continuity for AI coding agents: a reviewed task-state ledger served over MCP.
    A