MCP.Market

Modelbound MCP server

by ModelBound·io.github.ModelBound/modelbound-mcp·v0.1.2·1 stars
No reviews yet

Local-first MCP server for agent skills. Validate, lint, diff, and convert across IDEs.

B82/100grade B
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
B82/100

full report

Adoption
Growing

1 stars78 downloads/wk

Reviews

Write one

Nobody has reviewed Modelbound yet.

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

Modelbound tools (14, 2 write)

write = sends, deletes, buys or posts

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

  • convert_skill

    Convert a skill file from one IDE format to another (e.g. cursor → claude). Round-trips through a canonical {frontmatter, body} representation.

  • detect_ide_layout

    Detect which IDE skill/rule layouts exist in the current working directory. Returns the list of matching adapters (e.g. cursor, claude, kiro). Local-only, no network.

  • diff_skill

    Diff a local skill file against its cloud counterpart by slug. Local-side diff is computed here; the cloud half requires MODELBOUND_API_KEY.

  • get_context_health

    Get token health scores and staleness for your context library. Requires MODELBOUND_API_KEY.

  • install_marketplace_skill

    Install a public marketplace skill into your library. Requires MODELBOUND_API_KEY.

  • lint_skill

    Lint a skill file: front-matter, token count, broken links, TODO markers. Local-only.

  • list_cloud_skills

    List skills in the cloud library. Requires MODELBOUND_API_KEY.

  • list_local_skills

    List all skill / rule files found in the detected IDE directories under the current working directory.

  • pull_skill

    Pull a skill from the ModelBound cloud library. Requires MODELBOUND_API_KEY.

  • push_skillwrite action

    Create or update a skill in the cloud library. Requires MODELBOUND_API_KEY.

  • read_local_skill

    Read a local skill file (raw contents). Path must be inside the current working directory.

  • search_cloud

    Full-text search across all cloud content. Requires MODELBOUND_API_KEY.

  • validate_skill_format

    Validate a skill file against the agentskills.io standard.

  • write_local_skillwrite action

    Write a local skill file. Creates parent directories. Path must be inside the current working directory.

Public scan report

scanner v0.1.9 · 2026-09-27 · same rubric, same numbers if you re-run it

no findings
  • Code scan17 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 qualitystatic API keys via environment variables6/15
  • Maintenancelast push 1 days ago15/15
  • Maintainer identityregistry namespace matches repository owner7/10
Overall 82/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Modelbound compares

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

Safety score
82/100
higher than 65% of 4,460 AI and agents servers
Tools
14
the typical AI and agents server has 6
Tools that change things
14%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
1
more than 50% of 2,711 AI and agents servers
Downloads a week
78
more than 58% of 1,538 AI and agents servers with a package

What its tools let an agent do: 11 read · 1 create · 1 change · 1 run or deploy

Install Modelbound in Claude Code, Cursor or VS Code

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

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

What the publisher says

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

modelbound-mcp

Local-first MCP server for agent skills. Validate, lint, diff, and convert agent skill files across Cursor, Claude, Codex, Kiro, Windsurf, VS Code, and Amazon Q — no account required. Optional cloud sync with ModelBound.

Why ModelBound?

AI tools come and go. You might use Cursor today, switch to Claude Code tomorrow, and try Kiro next week — but your skills, rules, and context shouldn't be locked into any one of them. ModelBound gives you a single place to store and manage your agent skills, so you can move between tools freely without rebuilding your setup each time. Write a skill once, sync it everywhere, and get more value out of every AI subscription you're already paying for.

What it does

modelbound-mcp is a small Model Context Protocol server you run locally over stdio. It exposes tools to your IDE / agent using dot-notation naming for navigable discovery:

Local (no API key, no network):

  • ide.detectLayout — find which IDE conventions your repo uses
  • skills.listLocal, skills.readLocal, skills.writeLocal
  • skills.lint — front-matter, token count, broken links, TODO scan, trust score (scanner h5)
  • skills.trust — deterministic slop/trust heuristics without full lint
  • skills.scaffold — create a skill with default scope constraints
  • skills.reviewStatus, skills.reviewRequest, skills.reviewApprove, skills.reviewReject, skills.reviewGate
  • skills.validateFormat — agentskills.io compliance
  • skills.convert — translate between IDE formats (e.g. Cursor → Claude)
  • skills.diff — compare a local skill with its cloud counterpart

Cloud (with MODELBOUNDAPIKEY):

  • cloud.pullSkill, cloud.pushSkill, cloud.search
  • cloud.listSkills — now accepts aitype and sourceplatform filters; every row includes aitype, sourceplatform, source_path, and repo
  • cloud.resourceTree — returns the team's full hierarchy grouped by platform → top-level dir (.claude/skills, .cursor/rules, .kiro/steering, …) → files. Use this before cloud.listSkills when an orchestrator needs to map context before loading.
  • cloud.installMarketplaceSkill
  • optimization.health

Resource hierarchy

Orchestrators that juggle multiple AI platforms can call cloud.resourceTree once to get a complete map of available skills, rules, hooks, steering files, and system prompts — grouped exactly how each platform expects them on disk. Pair it with the new aitype / sourceplatform filters on cloud.listSkills to load only the slice you need. See examples/resource-tree.ts.

The cloud tools are a thin JSON-RPC proxy to mcp.modelbound.co. All business logic stays server-side; this repo never touches your data or secrets.

Migration from 0.1.x — old snakecase names (detectidelayout, pullskill, …) were removed in 0.2.0. The hosted ModelBound MCP server still accepts both forms forever for backward compatibility.

Anti-slop (0.4.x) — trust scanner bumped to h5 with scope-limit, unbounded-wording, dependency, and refactor findings. skills.readLocal now returns trustscore, scannerversion, reviewstate, and reviewmeta. Override default scope limits via .modelbound/task-budgets.json. Use skills.reviewGate in CI to block unapproved skills.

Install

npx modelbound-mcp

Or install globally:

npm i -g modelbound-mcp

Use as an MCP server

Cursor (.cursor/mcp.json)

Shortened. The full README is on GitHub.

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

Modelbound: common questions

Is Modelbound MCP server safe?
Mostly: it is graded B (82/100). Read the Modelbound safety report
How do I install Modelbound?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Modelbound need an API key?
Yes. The registry entry asks for MODELBOUND_API_KEY.
Is Modelbound maintained?
The last commit was 38 days ago (2026-09-27). The latest release is v0.1.2.
What can I use instead of Modelbound?
Servers from other publishers that do the same job: Skillsmith MCP server, LLM Sandbox MCP server and Basic Memory MCP server.
How does Modelbound compare with other AI and agents MCP servers?
safety score 82/100 (higher than 65% of 4,460 AI and agents servers); tools 14 (the typical AI and agents server has 6); tools that change things 14% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Modelbound

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

  • Skillsmith
    Share agent skills across your team, scan them for risk, and track what's actually used.
    B
  • LLM Sandbox
    Securely run LLM-generated code in isolated containers across 7 languages and 3 container backends.
    A
  • Basic Memory
    Local-first knowledge management with bi-directional LLM sync via Markdown files.
    B
  • HOL Guard
    Local-first AI agent security evidence and approval workflows through HOL Guard's stdio MCP server.
    A
  • Pm Claude Skills
    1310 professional Agent Skills + workflow recipes — searchable & fetchable over MCP.
    A