- Conduid
- Marketplace
- #specification
MCP servers tagged specification
66 live MCP servers tagged "specification", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with specification.
Utcp Specification
The specification for the Universal Tool Calling Protocol
Security Standard
MCP Server Security Standard (MSSS): an open, testable security control standard for certifying MCP servers, with levels, evidence requirements, and reporting schemas.
Ucp
Universal Context Package - an open specification for packaging work context for LLMs
Specification.website
Website specification — HTML, accessibility, security, SEO, agent-readiness. Platform-agnostic, sourced, MIT.
Agent Plugins Spec
Agent Plugins Specification v1.0.0 — A minimal standard for packaging agent extensions into distributable plugins
Open Memory Protocol
Open Memory Protocol — open spec for AI-agent memory: recall, remember, link, observe, validate. CC BY 4.0.
Specky
Agentic Spec-Driven Development — 13 agents, 58 MCP tools, 10-phase enforced pipeline. From meeting transcript to PR in one command. Install via npm install -g specky-sdd@latest
Schema
TypeScript types and JSON Schema for MCP server specifications. Define, validate, and share static snapshots of Model Context Protocol servers.
acm
MCP (Model Context Protocol) tool integration for ACM
Identity Spec
AGNTCY Identity allows to onboard, create and verify identities for Agents, Model Context Protocol (MCP) Servers and Multi-Agent Systems (MASs).
Neural Computation Protocol
Neural Computation Protocol (NCP): composable, sandboxed Bricks + graphs for auditable, replayable agentic systems.
Trail Spec
TRAIL — Tracking Records Across Isolated Logs. An open protocol for cross-MCP content tracking and deduplication.
MIF
Open standard for portable AI knowledge interchange — JSON-LD + Markdown dual format with W3C PROV provenance, bi-temporal tracking, entity relationships, and OKF support.
Abx Spec Behaviors
🧩 Proposal to allow user scripts like "expand comments", "hide popups", "fill out this form", etc. to be reusable across pure browser environments, puppeteer, playwright, extensio…
Stop Protocol
STOP — Skill Transparency & Observability Protocol. Making Agent Skills transparent, debuggable, and trustworthy.
Sekkei MCP Server
MCP Server for generating Japanese software specification documents following V-model
Server Inverspec
MCP server that reverse-engineers technical specifications from source code in eight phases (Inverspec workflow).
Dotdog
CLI tool for structured software specifications. Validate .dog files, compile .dag graphs, query via MCP.
StemJSON
Generative UI specification for native mobile: a declarative JSON language in which AI agents write a whole feature, its data, logic and navigation included, and the iOS and Andro…
Aifeels Reference
Official Python reference implementation of the Aifeels specification
Claude Agents Forge
Build and run production-ready Claude Code agents with full agent specs, including turn limits, permissions, memory, and tool orchestration.
Specsgraph Skills
Agent Skills for SpecsGraph: turn Claude Code, Cursor, Codex and GitHub Copilot into a domain-modelling partner over the SpecsGraph MCP server.
AI Native Office Spec
A technical specification for the AI-Native Office: the room as the machine, and the sovereign compute substrate that regulated enterprises need before autonomous AI agents can la…
Geospatial MCP
Open geospatial MCP standard for analyst, map, and app-builder workflows
Loopspec
MCP server + CLI that makes AI coding assistants smarter — persistent memory, drift detection, goal tracking, dependency graphs. Zero API calls. 125 tests. 42 tools.
Delegation Chain Spec
ADCS: open spec for agent-to-agent delegation chains — scope intersection, budget propagation, cycle prevention, audit.
A Protocol
MCP-A -- the MCP Answers Profile: a specialization of MCP that returns compiled, precise, structured answers. v1.0-beta.
Clavenar Specs
Technical specifications for Clavenar — TECH_SPEC.md is the source of truth for every wire contract across the clavenar-* repos.
Employee Md
📋 Open standard for AI agent employment contracts — YAML spec, JSON Schema, Python CLI validator, runtime SDK
Openwop
OpenWOP: the open-source protocol for multi-agent workflow orchestration. Run AI agents as workflows you can watch, pause for human approval and replay, on any host that implement…
MaxOS Spec
MaxOS turns AI agents into persistent, owned, policy-bounded, and auditable worker identities.
Local Spec
MCP Servers discovery spec
LogicSpec
YAML DSL for designing application feature logic — validate it, visualize it (VS Code canvas, Mermaid, Obsidian), and let AI agents read and write it via MCP
Tool Card Spec
MCP Tool Cards v0.1 draft. Per-tool disclosure documents for Model Context Protocol servers: input/output schema, side-effect classification, tested-LLM matrix, latency, cost, aud…
Bun Sticky Faf
FAF CLI for Bun — zero-dependency .faf parser and validator
Ribosome Schema
The ribosome standard: normative JSON Schemas for ribosome.json/ribosome.lock.json, generated types, validation, and a conformance corpus.
Sempods Spec
The sempods specification — the contract a semantic pod implements: contexts, grants, OAuth, LOD CRUD, SPARQL, find. Reference implementation: sempods-kotlin.
Faf Foundation Site
FAF Foundation website — stewards of the AI context standard
Prespec
Give your coding agent the spec before it writes the code. Curated behaviour cases served over MCP.
AI Native Medical Spec
Sovereign Clinical AI Edge Infrastructure — a vendor-neutral technical specification for building-integrated, zero-egress compute that lets autonomous clinical AI operate on Prote…
Pilotage
Pilotage: an open MCP extension for guided program authoring and verified execution. Schemas teach the moves; Pilotage teaches the game.
Open Toolset Protocol
Open Agent Toolset Protocol (OATP) - universal spec for AI agent tool discipline, structural instrumentation, and deterministic execution. Vendor-agnostic interop layer for availa…
Speclan Essentials
Companion tools and reference patterns for SPECLAN, the VS Code extension for spec-driven development with hierarchical Goal/Feature/Requirement specs as Markdown files in Git.
Themissinglayer
Architecture for coherence wherever AI moves faster than humans can synchronize.
Entity Discovery Protocol
Entity Discovery Protocol - A standardized protocol for AI agents to discover and verify digital entity information
Nika Spec
The Nika language spec. Nine keys, four verbs, a conformance suite anyone can run. Apache-2.0.
Finance Md
The standard that encodes financial conventions for AI agents and modeling tools
GitForStrategy
Strategic thinking as installable infrastructure — 21 skills, 13 seed patterns, 5-phase pipeline. Give your AI agent the discipline to explore, decide, execute, and learn.
Data Dignity Standard
Open standards and tools from the team building ArrowMem.
Harness Protocol
Open spec for portable AI coding agent configuration