# Agent Skills vs Model Context Protocol

The map lists them as complementary: sites and agents commonly implement both.

[5 Act](/category/act/) [Agent Skills](/protocols/anthropic-agent-skills-format/) · [5 Act](/category/act/) [Model Context Protocol](/protocols/mcp/)

|  | [Agent Skills](/protocols/anthropic-agent-skills-format/) | [Model Context Protocol](/protocols/mcp/) MCP |
| --- | --- | --- |
| Lifecycle step | 5 Act: Do something for me | 5 Act: Do something for me |
| Answers | How can reusable, on-demand procedural instructions and bundled resources be packaged so any compatible agent can load and run them? | How does an AI application call tools and pull structured context, prompts, and data from an external server? |
| Governed by | Originally developed and released as an open format by Anthropic; now described by its own site as "open to contributions from the broader ecosystem" with development happening in the community-run github.com/agentskills/agentskills org and a public Discord | Agentic AI Foundation (Linux Foundation umbrella); day-to-day spec work in the modelcontextprotocol GitHub org via public SEPs (Specification Enhancement Proposals) and working groups |
| Status (issuer's words) | Active open format, described on agentskills.io as adopted by a growing number of agent products | Active open specification, current dated release 2026-07-28 |
| Phase | living | living |
| Version | unversioned living spec (agentskills.io/specification) | 2026-07-28 (2026-07-28) |
| Form / transport | document format | endpoint |
| Found at | <skill-name>/SKILL.md (directory name must match the frontmatter name field) | GET {endpoint}/server-card (SEP-2127 Final, application/mcp-server-card+json, discovered via /.well-known/ai-catalog.json; /.well-known/mcp.json is legacy SEP-1649) |
| Adoption | observed | measured — Three independent registry censuses, kept separate and not averaged. VerifyMCP as of 2026-10-19 (https://verifymcp.io/stats): 47,870 logical servers (45,953 active, 601 deprecated, 1,316 deleted; 31,337 remote; 30,842 Streamable HTTP; among handshook components, 20,031 on 2025-11-25 and 6,571 on 2026-07-28). Registry Discussion 1580 as of 2026-08-27 (https://github.com/modelcontextprotocol/registry/discussions/1580): a cursor walk of 82,994 version records yielding 25,125 distinct isLatest servers across 15,468 publishers (13,279 Streamable HTTP remotes). Registry Discussion 1548 as of 2026-08-19 (https://github.com/modelcontextprotocol/registry/discussions/1548): 22,636 active latest registrations (12,077 declaring an HTTPS remote). |
| Evidence | 2 verified | 11 verified, 2 reported |
| Primary use case | Describe an agent's capabilities | Expose tools to agents |
| Last verified | 2026-10-22 (current) | 2026-10-22 (current) |
| Specification | [https://agentskills.io/specification](https://agentskills.io/specification) | [https://modelcontextprotocol.io/specification/2026-07-28/index](https://modelcontextprotocol.io/specification/2026-07-28/index) |

## When to use which

- Choose Agent Skills when your question is “How can reusable, on-demand procedural instructions and bundled resources be packaged so any compatible agent can load and run them?” and you accept its maturity: phase living, adoption observed.
- Choose Model Context Protocol when your question is “How does an AI application call tools and pull structured context, prompts, and data from an external server?” and you accept its maturity: phase living, adoption measured (Three independent registry censuses, kept separate and not averaged. VerifyMCP as of 2026-10-19 (https://verifymcp.io/stats): 47,870 logical servers (45,953 active, 601 deprecated, 1,316 deleted; 31,337 remote; 30,842 Streamable HTTP; among handshook components, 20,031 on 2025-11-25 and 6,571 on 2026-07-28). Registry Discussion 1580 as of 2026-08-27 (https://github.com/modelcontextprotocol/registry/discussions/1580): a cursor walk of 82,994 version records yielding 25,125 distinct isLatest servers across 15,468 publishers (13,279 Streamable HTTP remotes). Registry Discussion 1548 as of 2026-08-19 (https://github.com/modelcontextprotocol/registry/discussions/1548): 22,636 active latest registrations (12,077 declaring an HTTPS remote).).

Guidance is derived from the two records (question, phase, adoption, prerequisites, pairings), not from opinion. Each record's page carries its numbered references.

## Read the full articles

- [Agent Skills](/protocols/anthropic-agent-skills-format/): How can reusable, on-demand procedural instructions and bundled resources be packaged so any compatible agent can load and run them?
- [Model Context Protocol](/protocols/mcp/): How does an AI application call tools and pull structured context, prompts, and data from an external server?

Ask the MCP server to compare any two: the compare-protocols prompt, or get on both ids. [Connect](/connect/).

[anthropic-agent-skills-format.json](/data/protocols/anthropic-agent-skills-format.json) · [mcp.json](/data/protocols/mcp.json) · [Markdown](/compare/anthropic-agent-skills-format-vs-mcp/index.md)