Model Context Protocol (MCP) vs agents.json
The map lists them as complementary: sites and agents commonly implement both.
| Model Context Protocol MCP | agents.json | |
|---|---|---|
| Lifecycle step | 5 Act: Do something for me | 5 Act: Do something for me |
| Answers | How does an AI application call tools and pull structured context, prompts, and data from an external server? | How does an agent learn which multi-step API call sequences ("flows") a service supports, on top of its raw OpenAPI surface? |
| Governed by | 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 | Wildcard AI; single company controls the spec and the reference "Wildcard Bridge" runtime and maintains a discretionary registry of published files |
| Status (issuer's words) | Active open specification, current dated release 2026-07-28 | Dormant: last push 2025-08-21, version 0.1.0 |
| Version | 2026-07-28 (2026-07-28) | 0.1.0 (2025-03) |
| Form / transport | endpoint | well-known file |
| Found at | 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) | /.well-known/agents.json (proposed; not mandatory, per the spec's own FAQ) |
| Implementation | multi-implementation — Three independent registry censuses, kept separate and not averaged. VerifyMCP as of 2026-10-19 (https://verifymcp.io/stats, embedded in <script id="stats-charts-data"> time-series JSON; HTML hero card reflects latest daily snapshot): 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). | prototype |
| Evidence | 11 verified, 2 reported | 4 verified, 2 reported |
| Primary use case | Expose tools to agents | Let agents discover my API or service |
| Last verified | 2026-10-23 (current) | 2026-10-23 (current) |
| Specification | https://modelcontextprotocol.io/specification/2026-07-28/index | https://github.com/wild-card-ai/agents-json |
When to use which
- 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: status "Active open specification, current dated release 2026-07-28", implementation multi-implementation (Three independent registry censuses, kept separate and not averaged. VerifyMCP as of 2026-10-19 (https://verifymcp.io/stats, embedded in <script id="stats-charts-data"> time-series JSON; HTML hero card reflects latest daily snapshot): 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).).
- Choose agents.json when your question is “How does an agent learn which multi-step API call sequences ("flows") a service supports, on top of its raw OpenAPI surface?” and you accept its maturity: status "Dormant: last push 2025-08-21, version 0.1.0", implementation prototype. It is no longer maintained; prefer its successor.
Read the full articles
- Model Context Protocol: How does an AI application call tools and pull structured context, prompts, and data from an external server?
- agents.json: How does an agent learn which multi-step API call sequences ("flows") a service supports, on top of its raw OpenAPI surface?