{ "id": "ep7wtkzh9y", "slug": "model-context-protocol", "title": "Model Context Protocol", "updated": "2026-10-15", "topic_path": [ { "id": "technology", "label": "Technology and the built world", "api_url": "https://www.edgepedia.org/api/v1/topics/technology" }, { "id": "technology.computing", "label": "Computing and digital systems", "api_url": "https://www.edgepedia.org/api/v1/topics/technology.computing" }, { "id": "technology.computing.modern_ai", "label": "Modern AI: foundation models, generative AI, and the AI industry", "api_url": "https://www.edgepedia.org/api/v1/topics/technology.computing.modern_ai" }, { "id": "technology.computing.modern_ai.methods", "label": "Foundation-model methods and training", "api_url": "https://www.edgepedia.org/api/v1/topics/technology.computing.modern_ai.methods" }, { "id": "technology.computing.modern_ai.methods.prompting_reasoning_agents", "label": "Prompting, reasoning, and agents", "api_url": "https://www.edgepedia.org/api/v1/topics/technology.computing.modern_ai.methods.prompting_reasoning_agents" } ], "geo": [ { "id": "geo.us.t2021.technology.computing.modern_ai.methods.prompting_reasoning_agents", "label": "United States · 2021 and later: Prompting, reasoning, and agents", "api_url": "https://www.edgepedia.org/api/v1/geo/geo.us.t2021.technology.computing.modern_ai.methods.prompting_reasoning_agents", "path": [ { "id": "geo.us", "label": "United States", "api_url": "https://www.edgepedia.org/api/v1/geo/geo.us" }, { "id": "geo.us.t2021", "label": "United States · 2021 and later", "api_url": "https://www.edgepedia.org/api/v1/geo/geo.us.t2021" }, { "id": "geo.us.t2021.technology", "label": "Technology and the built world", "api_url": "https://www.edgepedia.org/api/v1/geo/geo.us.t2021.technology" }, { "id": "geo.us.t2021.technology.computing", "label": "Computing and digital systems", "api_url": "https://www.edgepedia.org/api/v1/geo/geo.us.t2021.technology.computing" }, { "id": "geo.us.t2021.technology.computing.modern_ai", "label": "Modern AI: foundation models, generative AI, and the AI industry", "api_url": "https://www.edgepedia.org/api/v1/geo/geo.us.t2021.technology.computing.modern_ai" }, { "id": "geo.us.t2021.technology.computing.modern_ai.methods", "label": "Foundation-model methods and training", "api_url": "https://www.edgepedia.org/api/v1/geo/geo.us.t2021.technology.computing.modern_ai.methods" }, { "id": "geo.us.t2021.technology.computing.modern_ai.methods.prompting_reasoning_agents", "label": "Prompting, reasoning, and agents", "api_url": "https://www.edgepedia.org/api/v1/geo/geo.us.t2021.technology.computing.modern_ai.methods.prompting_reasoning_agents" } ] } ], "excerpt": "The Model Context Protocol (MCP) is an open standard released by Anthropic in 2024 that connects AI applications to external tools and data sources, adopted by OpenAI, Google DeepMind, and Microsoft.", "snippet": "The Model Context Protocol (MCP) is an open standard released by Anthropic in 2024 that connects AI applications to external tools and data sources, adopted by OpenAI, Google DeepMind, and Microsoft.", "node": "technology.computing.modern_ai.methods.prompting_reasoning_agents", "markdown": "# Model Context Protocol\n\nThe Model Context Protocol (MCP) is an open, JSON-RPC 2.0-based standard, released by [Anthropic](https://www.edgepedia.org/anthropic) on November 25, 2024, that defines how AI applications connect to external tools, data sources, and workflows. It was created at Anthropic by David Soria Parra and Justin Spahr-Summers and open-sourced with the specification, Python and TypeScript SDKs, and reference servers.[1](https://temperature2.com/p/2026-09-11-guide-what-is-mcp/) • [2](https://www.anthropic.com/news/model-context-protocol?guides=image-generation-social-good) Since December 9, 2025 it has been stewarded by the Agentic AI Foundation, a directed fund under the [Linux Foundation](https://www.edgepedia.org/linux-foundation).[1](https://temperature2.com/p/2026-09-11-guide-what-is-mcp/)\n\nAnthropic's stated aim was to replace fragmented, one-off integrations between AI assistants and the systems where their data lives with a single universal protocol.[2](https://www.anthropic.com/news/model-context-protocol?guides=image-generation-social-good) By 2026 the protocol had been adopted by OpenAI, Google DeepMind, and Microsoft as well as Anthropic, and the ecosystem counted thousands of public servers.[3](https://agen.co/learning-center/model-context-protocol)\n\n| Fact | Detail |\n|---|---|\n| Announced | November 25, 2024, open-sourced by Anthropic[1](https://temperature2.com/p/2026-09-11-guide-what-is-mcp/) |\n| Creators | David Soria Parra and Justin Spahr-Summers at Anthropic[2](https://www.anthropic.com/news/model-context-protocol?guides=image-generation-social-good) |\n| Basis | JSON-RPC 2.0 messaging over stdio or Streamable HTTP transports[4](https://github.com/modelcontextprotocol/modelcontextprotocol/blob/main/docs/specification/2026-07-28/index.mdx) • [5](https://modelcontextprotocol.io/docs/2026%2D07%2D28/learn/architecture) |\n| Core primitives | Tools (executable functions), Resources (contextual data), Prompts (reusable templates)[5](https://modelcontextprotocol.io/docs/2026%2D07%2D28/learn/architecture) |\n| Governance | Donated to the Linux Foundation's Agentic AI Foundation on December 9, 2025[1](https://temperature2.com/p/2026-09-11-guide-what-is-mcp/) |\n| Ecosystem scale | 10,000+ public servers and 97M+ monthly SDK downloads at December 2025 (donation figures)[1](https://temperature2.com/p/2026-09-11-guide-what-is-mcp/) |\n| Current spec | 2026-07-28: stateless, per-request capability negotiation, sampling deprecated[4](https://github.com/modelcontextprotocol/modelcontextprotocol/blob/main/docs/specification/2026-07-28/index.mdx) • [1](https://temperature2.com/p/2026-09-11-guide-what-is-mcp/) |\n\n## What MCP is\n\nMCP is an open-source standard for connecting AI applications such as Claude or ChatGPT to external systems: data sources like local files and databases, tools like search engines and calculators, and workflows.[6](https://modelcontextprotocol.io/docs/2026-07-28/getting-started/intro) The protocol uses JSON-RPC 2.0 messages for communication.[4](https://github.com/modelcontextprotocol/modelcontextprotocol/blob/main/docs/specification/2026-07-28/index.mdx)\n\nThe architecture follows a client-server model. An MCP host, an AI application like [Claude Code](https://www.edgepedia.org/claude-code) or Claude Desktop, establishes connections to one or more MCP servers by creating one MCP client for each server, each with a dedicated connection.[5](https://modelcontextprotocol.io/docs/2026%2D07%2D28/learn/architecture) A server is the program that exposes tools and data; the host is the AI application the user actually runs.\n\n## How it works\n\nMCP consists of two layers. The data layer defines the JSON-RPC-based protocol for client-server communication, including capability discovery and the primitives. The transport layer defines how connections are established, how messages are framed, and how authorization works.[5](https://modelcontextprotocol.io/docs/2026%2D07%2D28/learn/architecture)\n\nServers expose three core primitives. Tools are executable functions an AI application can invoke to perform actions, such as file operations, API calls, or database queries. Resources are contextual data the application can read. Prompts are reusable interaction templates.[5](https://modelcontextprotocol.io/docs/2026%2D07%2D28/learn/architecture)\n\nTwo transports are defined. The stdio transport uses standard input and output streams for direct communication between local processes on the same machine. The Streamable HTTP transport, built on HTTP POST with optional Server-Sent Events, serves remote servers, and MCP recommends using [OAuth](https://www.edgepedia.org/oauth) to obtain authentication tokens.[5](https://modelcontextprotocol.io/docs/2026%2D07%2D28/learn/architecture)\n\nThe current specification, dated 2026-07-28, is a stateless rewrite: the initialize handshake and session IDs were removed and replaced by per-request protocol version and capability declarations, so every request is self-contained and negotiates its own capabilities.[4](https://github.com/modelcontextprotocol/modelcontextprotocol/blob/main/docs/specification/2026-07-28/index.mdx) • [1](https://temperature2.com/p/2026-09-11-guide-what-is-mcp/) Sampling, a mechanism by which servers could request model completions from the client, is deprecated as of this version.[5](https://modelcontextprotocol.io/docs/2026%2D07%2D28/learn/architecture)\n\n## Origin and design lineage\n\nMCP was created at Anthropic by David Soria Parra and Justin Spahr-Summers.[2](https://www.anthropic.com/news/model-context-protocol?guides=image-generation-social-good) The specification states that MCP takes inspiration from the [Language Server Protocol](https://www.edgepedia.org/language-server-protocol) (LSP), which standardized how to add support for programming languages across a whole ecosystem of development tools; MCP applies the same idea to connecting AI applications to context and tools.[4](https://github.com/modelcontextprotocol/modelcontextprotocol/blob/main/docs/specification/2026-07-28/index.mdx)\n\nThe problem it targeted was integration scale. Before November 2024, most AI applications used proprietary function-calling formats tied to one vendor's API, so each new tool or data source meant a new custom integration; MCP's stated alternative to that N-times-M problem is one protocol that any host and any server can speak.[1](https://temperature2.com/p/2026-09-11-guide-what-is-mcp/) [Function calling](https://www.edgepedia.org/function-calling) and MCP are complementary rather than competing layers: function calling is the model capability to emit a structured request to invoke a function, while MCP defines where those functions live, how they are discovered, and how the call is transported and secured.[3](https://agen.co/learning-center/model-context-protocol)\n\n## Adoption and ecosystem\n\nAt launch, Anthropic released the specification and SDKs, local MCP server support in Claude Desktop, and pre-built servers for [Google Drive](https://www.edgepedia.org/google-drive), Slack, GitHub, Git, Postgres, and Puppeteer. Early adopters Block and Apollo integrated MCP into their systems, while development-tool companies Zed, Replit, Codeium, and [Sourcegraph](https://www.edgepedia.org/sourcegraph) worked with it.[2](https://www.anthropic.com/news/model-context-protocol?guides=image-generation-social-good)\n\nCompeting vendors followed. OpenAI, [Google DeepMind](https://www.edgepedia.org/google-deepmind), and Microsoft have all adopted or integrated MCP across their AI products and developer tooling.[3](https://agen.co/learning-center/model-context-protocol) In 2025 OpenAI added MCP support to its Agents SDK, and Google DeepMind added it for Gemini.[1](https://temperature2.com/p/2026-09-11-guide-what-is-mcp/) OpenAI added full MCP client support in ChatGPT in late 2025; Google shipped official MCP support and a managed Gemini remote server in mid-2026; and Microsoft ships MCP in VS Code, Copilot, and the Microsoft Agent Framework (release candidate February 19, 2026).[7](https://alicelabs.ai/en/insights/model-context-protocol-guide-2026) As of the 2026-07-28 documentation, the assistants Claude and ChatGPT, and the development tools [Visual Studio Code](https://www.edgepedia.org/visual-studio-code), Cursor, and MCPJam all support MCP.[6](https://modelcontextprotocol.io/docs/2026-07-28/getting-started/intro)\n\n## By the numbers\n\nEcosystem metrics vary by counting method, and vendor-reported and independent figures should be kept apart.\n\n- At the December 2025 donation, Anthropic-reported figures put the ecosystem at over 10,000 active public MCP servers and 97 million-plus monthly SDK downloads, up from roughly 100,000 monthly downloads at the November 2024 launch.[1](https://temperature2.com/p/2026-09-11-guide-what-is-mcp/)\n- The official MCP Registry API held 9,652 latest server records as of May 24, 2026. An independent Nerq census counted 17,468 servers across all registries in Q1 2026, and the directory Glama indexes close to 20,000 servers by 2026.[7](https://alicelabs.ai/en/insights/model-context-protocol-guide-2026)\n- Download estimates conflict: one source reports close to half a billion SDK downloads a month as of mid-2026,[8](https://www.scaler.com/topics/agentic-ai/model-context-protocol/) roughly five times the 97 million figure reported for December 2025.[1](https://temperature2.com/p/2026-09-11-guide-what-is-mcp/) Registry counts, which are direct censuses, are a firmer measure of ecosystem size.\n\n## Security and incidents\n\nSeveral risk classes are documented for MCP deployments. Indirect prompt injection, which OWASP ranks as the top risk for LLM applications, is the mechanism behind most agent hijacking, and it applies to any system where a model reads untrusted text that can influence tool use.[3](https://agen.co/learning-center/model-context-protocol) Tool poisoning and rug pulls, where a server's advertised behavior differs from or changes after approval, and data exfiltration are also documented risks.[3](https://agen.co/learning-center/model-context-protocol)\n\nThe specification itself treats tool metadata with suspicion: tools represent arbitrary code execution, descriptions of tool behavior such as annotations should be considered untrusted unless obtained from a trusted server, and hosts must obtain explicit user consent before invoking any tool.[4](https://github.com/modelcontextprotocol/modelcontextprotocol/blob/main/docs/specification/2026-07-28/index.mdx) Confused-deputy authorization, where a legitimate server is tricked into misusing its credentials, was a documented attack class that the 2026-07-28 authorization changes exist largely to close.[3](https://agen.co/learning-center/model-context-protocol)\n\nThe specification is explicit about the protocol's own boundary: while MCP cannot enforce security principles at the protocol level, implementors should build robust consent and authorization flows into their applications.[4](https://github.com/modelcontextprotocol/modelcontextprotocol/blob/main/docs/specification/2026-07-28/index.mdx)\n\n## How it compares\n\n**MCP versus function calling.** Function calling is the model-side mechanism: the LLM emits a structured JSON tool call. MCP is the protocol layer that standardizes how that call is discovered, executed, and returned across processes and vendors.[7](https://alicelabs.ai/en/insights/model-context-protocol-guide-2026) In native function calling, tools are declared statically at prompt time; with MCP, a host discovers available tools dynamically via a tools/list call, which makes the same tool set portable across hosts and vendors.[7](https://alicelabs.ai/en/insights/model-context-protocol-guide-2026) • [3](https://agen.co/learning-center/model-context-protocol)\n\n**MCP versus direct REST integrations.** MCP typically wraps existing APIs rather than replacing them. A traditional API is built for a developer to call from code at build time; MCP is built for an AI model to discover and call at runtime, with machine-readable schemas and descriptions designed for a model to reason about. For a single internal integration that will never be reused, a direct API call can be simpler.[3](https://agen.co/learning-center/model-context-protocol) • [1](https://temperature2.com/p/2026-09-11-guide-what-is-mcp/)\n\n**MCP versus Google's Agent2Agent (A2A).** The two address different layers: MCP connects an AI application to tools and data, while A2A focuses on how autonomous agents communicate and delegate to each other. They are frequently used together rather than in competition.[3](https://agen.co/learning-center/model-context-protocol)\n\n## Governance and what changed in 2025–2026\n\nOn December 9, 2025, Anthropic donated MCP to the Agentic AI Foundation, a directed fund under the Linux Foundation, alongside Block's goose and OpenAI's AGENTS.md as founding projects.[1](https://temperature2.com/p/2026-09-11-guide-what-is-mcp/) The move made MCP a vendor-neutral community standard with a published feature-lifecycle policy, removing sole stewardship by Anthropic.[3](https://agen.co/learning-center/model-context-protocol)\n\nThe 2026-07-28 specification revision followed under this governance. It rewrote the protocol to be stateless, removing the initialize handshake and session IDs in favor of per-request protocol version and capability declarations,[1](https://temperature2.com/p/2026-09-11-guide-what-is-mcp/) and included authorization changes aimed largely at closing the confused-deputy attack.[3](https://agen.co/learning-center/model-context-protocol) Sampling was deprecated in the same revision.[5](https://modelcontextprotocol.io/docs/2026%2D07%2D28/learn/architecture)\n\n## References\n\n1. [What is MCP (Model Context Protocol)? — temperature2 (2026-09-11)](https://temperature2.com/p/2026-09-11-guide-what-is-mcp/)\n2. [Introducing the Model Context Protocol — Anthropic](https://www.anthropic.com/news/model-context-protocol?guides=image-generation-social-good)\n3. [What Is the Model Context Protocol (MCP)? Complete Guide — Agen](https://agen.co/learning-center/model-context-protocol)\n4. [MCP Specification 2026-07-28 (GitHub)](https://github.com/modelcontextprotocol/modelcontextprotocol/blob/main/docs/specification/2026-07-28/index.mdx)\n5. [MCP Architecture (official docs, 2026-07-28)](https://modelcontextprotocol.io/docs/2026%2D07%2D28/learn/architecture)\n6. [MCP Getting Started / Introduction (official docs, 2026-07-28)](https://modelcontextprotocol.io/docs/2026-07-28/getting-started/intro)\n7. [Model Context Protocol (MCP) Guide 2026 — Alice Labs](https://alicelabs.ai/en/insights/model-context-protocol-guide-2026)\n8. [Model Context Protocol (MCP) — Scaler](https://www.scaler.com/topics/agentic-ai/model-context-protocol/)\n\n---\n*Topic: Encyclopedia › Technology and the built world › Computing and digital systems › Modern AI: foundation models, generative AI, and the AI industry › Foundation-model methods and training › Prompting, reasoning, and agents*\n\n*Initially written Sep 17, 2026 · Edited: Oct 11, 2026; Oct 15, 2026*\n\n*Copyright 2026 EdgeChat AI, a subsidiary of Biostate AI.*\n\nLicense: Edgepedia Community License 1.0, https://www.edgepedia.org/edgepedia/license\n", "same_as": [], "url": "https://www.edgepedia.org/model-context-protocol", "markdown_url": "https://www.edgepedia.org/model-context-protocol.md", "license": { "name": "Edgepedia Community License 1.0", "url": "https://www.edgepedia.org/edgepedia/license", "summary": "Free with credit, commercial use included. AI training is open to everyone. For other uses, organizations over USD 100M in revenue or 100M monthly users license separately.", "spdx": "LicenseRef-Edgepedia-Community-1.0" }, "credit": "\"Model Context Protocol\", Edgepedia (EdgeChat), https://www.edgepedia.org/model-context-protocol. Edgepedia Community License 1.0.", "credit_md": "\"[Model Context Protocol](https://www.edgepedia.org/model-context-protocol)\", Edgepedia (EdgeChat), [https://www.edgepedia.org/model-context-protocol](https://www.edgepedia.org/model-context-protocol). [Edgepedia Community License 1.0](https://www.edgepedia.org/edgepedia/license).", "credit_html": "\"Model Context Protocol\", Edgepedia (EdgeChat), https://www.edgepedia.org/model-context-protocol. Edgepedia Community License 1.0.", "speakable": "The Model Context Protocol is an open standard released by Anthropic in 2024 that connects AI applications to external tools and data sources, adopted by OpenAI, Google DeepMind, and Microsoft." }