Skip to content
Agentmart
Submit a tool

Modelbound MCP

Local-first MCP server for agent skills.

Connector by ModelBound · GitHub account verified by the MCP Registry

IndexedMITLocal (stdio)★ 1
Write a review

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/modelbound-modelbound-mcp

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

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

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list, install config and code. Checked Oct 26, 2026.

Tools
30 read · 16 write · 0 delete · 5 not yet classified
Secrets
1 (API keys, tokens or passwords)
Install scripts
None found
Runs as
Node.js package

Tools by what they do 51

Read from the source code; the running server may list different tools.

Read 30 · Look things up without changing anything.

  • check_harness
  • cloud.listSkills
  • cloud.resourceTree
  • cloud.search
  • eval.listCases
  • eval.listResults
  • ide.detectLayout
  • optimization.health
  • optimization.preview
  • pipeline.config
  • pipeline.status
  • skill.compareVersions
Show 18 more tools
  • skill.diff
  • skill.findings
  • skill.ignoreFinding
  • skill.reliability
  • skill.suggestImprovements
  • skill.testCases
  • skill.unignoreFinding
  • skill.versions
  • skills.checks
  • skills.convert
  • skills.diff
  • skills.flightCheck
  • skills.lint
  • skills.listLocal
  • skills.readLocal
  • skills.reviewGate
  • skills.reviewStatus
  • skills.validateFormat

Write 16 · Create, change, send or run things.

  • cloud.installMarketplaceSkill
  • cloud.pushSkill
  • eval.createCase
  • eval.run
  • optimization.dryRun
  • optimization.run
  • pipeline.run
  • report_run
  • skill.benchmark
  • skill.createTestCase
  • skill.test
  • skill.testRuns
Show 4 more tools
  • skills.scaffold
  • skills.writeLocal
  • sync.fromIde
  • workspace.setContext

Not yet classified 5 · We could not tell from the name and description.

  • cloud.pullSkill
  • skill.report_outcome
  • skills.reviewApprove
  • skills.reviewReject
  • skills.reviewRequest

Secrets and settings it asks for

Secrets: values you paste in that let it act as you.

  • MODELBOUND_API_KEY

Network hosts it talks to 5

  • api.modelbound.co · found in code
  • github.com · found in code
  • glama.ai · found in code
  • mcp.modelbound.co · found in code
  • modelbound.co · found in code

Files it touches

  • Any path the agent passes to its tools

Tools (51)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

  • check_harness

    Check whether a skill is cleared to run unattended. Returns a pass/warn/fail status across the four harness pillars (context, permissions, guardrails, verification) from the skill's latest pipeline run, with the reasons for anything blocking. Call this before using a skill for a task you will not review.

  • cloud.installMarketplaceSkill

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

  • cloud.listSkills

    List skills in the cloud library. Supports ai_type (skill|hook|steering|system-prompt|rule|agent|memory|spec|instructions|prompt) and source_platform (claude-code|cursor|kiro|amazon-q|copilot|windsurf|codex|agents|modelbound) filters. Each row includes ai_type, source_platform, source_path, and repo for hierarchy-aware orchestration. Requires MODELBOUND_API_KEY.

  • cloud.pullSkill

    Pull a skill from the ModelBound cloud library. Response includes ai_type, source_platform, source_path, and repo when known. Requires MODELBOUND_API_KEY.

  • cloud.pushSkill

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

  • cloud.resourceTree

    Return the team's full AI resource hierarchy grouped by platform → top-level directory (.claude/skills, .cursor/rules, .kiro/steering, …) → files. Use this BEFORE listSkills when an orchestrator needs to map available context before loading. Requires MODELBOUND_API_KEY.

  • cloud.search

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

  • eval.createCase

    Create a new eval test case (name, input_prompt, optional expected_output, rubric). Requires agent scope.

  • eval.listCases

    List all eval cases for the team. Requires agent scope.

  • eval.listResults

    List past eval results, optionally filtered by eval_case_id.

  • eval.run

    Submit actual output for scoring against an eval case. Pass score/pass for manual judging or omit for AI judge.

  • ide.detectLayout

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

  • optimization.dryRun

    Same as optimization.run but never writes. Returns projected savings. Safe to call from auto-suggest hooks. Requires MODELBOUND_API_KEY.

  • optimization.health

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

  • optimization.preview

    Fetch a cached optimized variant of a skill or file without re-running optimization. Useful when an agent wants the lean version for inference but the raw version for editing.

Show 36 more tools
  • optimization.run

    Run AI token optimization on a cloud skill, file, agent, or pack. Returns tokens_saved, savings_pct, version snapshot id, and a per-file breakdown. Requires MODELBOUND_API_KEY. Server creates a backup version automatically; for local-file edits the caller MUST snapshot via the BackupEngine first.

  • pipeline.config

    Read or update a skill's pipeline_config (max_latency_ms, enforce_latency/enforce_tests flags, default targets). Pass `config` to update; omit to read.

  • pipeline.run

    Run the Skill Development Pipeline (Test → Optimize → Production) on a skill. Streams stage results into skill_pipeline_runs. Returns { run_id, status, version_after }. Use pipeline.status to watch progress. Requires MODELBOUND_API_KEY.

  • pipeline.status

    Get pipeline run status. Pass run_id for a specific run, or skill_id + limit for recent runs. Poll every 1-2s while status === 'running'.

  • report_run

    Report a finished agent run to ModelBound so each step is tied to the skill that shaped it. Send step summaries only (name, kind, duration, tokens, status) — never prompts or outputs. Failed runs become outcome reports for the skill.

  • skill.benchmark

    Run benchmark latency suite for a skill. Requires MODELBOUND_API_KEY.

  • skill.compareVersions

    Compare two skill versions (e.g. latest vs current). Requires MODELBOUND_API_KEY.

  • skill.createTestCase

    Create a saved automated check test case for a skill. Requires skill_id, name, and prompt. Optional notes for grading.

  • skill.diff

    Return a unified diff between two versions of a skill (or between the live version and an arbitrary string). Use skill.versions first to find version labels.

  • skill.findings

    List safety and quality findings for a skill. Returns findings with stable keys, and ignored_keys. Requires MODELBOUND_API_KEY.

  • skill.ignoreFinding

    Ignore a finding by stable key (or class/severity/message). Requires MODELBOUND_API_KEY.

  • skill.reliability

    Read back how the team's skills have performed in real use (worked / partial / failed over a rolling window). Use it to pick the most reliable skill for a task, or to find the ones that need attention. Requires MODELBOUND_API_KEY.

  • skill.report_outcome

    Report how a skill performed after you used it. Call this once the task that used the skill is finished — it is how the skill gets improved. Keep excerpts short. Requires MODELBOUND_API_KEY.

  • skill.suggestImprovements

    Suggest skill improvements from findings, tests and real-world outcomes. Requires MODELBOUND_API_KEY.

  • skill.test

    Run a single skill test case against the live model. Pass test_case_id for a saved case or prompt + skill_md for an ad-hoc run. Returns adherence_score (1-10), verdict, latency_ms.

  • skill.testCases

    List saved test cases for a skill.

  • skill.testRuns

    List recent test runs for a skill (latest first).

  • skill.unignoreFinding

    Un-ignore a previously ignored finding. Requires MODELBOUND_API_KEY.

  • skill.versions

    List historical versions of a skill or file (from file_versions). Each entry includes version label, sha, created_at, and the actor that produced it.

  • skills.checks

    Check a local skill with deterministic heuristics (scanner h5). Returns pass / warn / fail with findings — no numeric score.

  • skills.convert

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

  • skills.diff

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

  • skills.flightCheck

    Flight Check: offline safety scan for a skill or prompt (prompt injection, exfiltration, secrets, destructive commands, wildcard tools, loop hazards, clarity, token budget). Pass a file path or raw content. Local-only, zero AI cost. Blocking findings should be fixed before shipping.

  • skills.lint

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

  • skills.listLocal

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

  • skills.readLocal

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

  • skills.reviewApprove

    Approve a skill; stores the approved body hash and checks status (pass, warn or fail) at approval time.

  • skills.reviewGate

    CI gate: exit semantics via blocked=true when skill is not approved.

  • skills.reviewReject

    Reject a skill with optional reviewer notes.

  • skills.reviewRequest

    Move a skill to pending_review.

  • skills.reviewStatus

    Show review_state, review_meta, check status, and confidence trend for a skill.

  • skills.scaffold

    Create a new SKILL.md with default scope constraints and draft review state.

  • skills.validateFormat

    Validate a skill file against the agentskills.io standard.

  • skills.writeLocal

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

  • sync.fromIde

    Sync a local skill file from the IDE to cloud and return a repo-linked skill UUID. Requires MODELBOUND_API_KEY.

  • workspace.setContext

    Set workspace context before skill list/get/test/pipeline ops. Scopes skills to the current repo by default. Requires MODELBOUND_API_KEY.

Signals

Stars
1
Forks
0
Open issues
0
Last commit
Oct 13, 2026 (16 days ago)
Last release
Oct 13, 2026 (16 days ago)

From GitHub (fetched Oct 24, 2026).

Details

Registry name
io.github.ModelBound/modelbound-mcp
Version
0.1.2
Auth
API key
Packages
npm modelbound-mcp
License
MIT
Repository
github.com/ModelBound/modelbound-mcp-server
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
Official MCP Registrygithub-graphql
Cite this page

Modelbound MCP. Agent Mart. https://agentmart.dev/connectors/modelbound-modelbound-mcp (last updated 2026-10-24)