Definition
Model Context Protocol (MCP) is an open-source protocol developed by Anthropic that enables AI models to connect to external tools, data sources, and applications. It serves as a standard for AI integration, similar to how USB provides a standard for hardware connections.
Overview
MCP provides a standardized way for AI systems to:
- Access external data sources
- Call APIs and services
- Perform actions in external applications
- Maintain context across interactions
2026 Adoption
Spec 2026-07-28 (July 2026)
- 2026-07-28: aaif / linux-foundation finalize MCP
2026-07-28— fully stateless core (noinitialize/Mcp-Session-Id), OAuth/OIDCisshardening, 12-month deprecation policy, official mcp-apps and mcp-tasks extensions (2026-07-28-mcp-official-blog-rc, 2026-07-28-mcp-2026-07-28-stateless-spec)
Warning
~250M weekly SDK downloads and AAIF ~240 members are maintainer/foundation-cited via VentureBeat — attribute.
Anthropic Claude Expansion
- Claude Connectors expanded to 200+ applications via MCP
- Consumer integrations: Uber, Spotify, Uber Eats, Instacart, TurboTax, Resy, Booking.com
- OAuth 2.0 authentication standard
- Privacy: No persistent data storage, no training on Enterprise/Team data
Sentry MCP Integration (Security Concern)
- sentry MCP server returns error events to ai-coding-tools as trusted structured output
- agentjacking exploit: injected error events indistinguishable from legitimate Sentry guidance
- Implicit trust model — agents cannot verify data provenance
Security Risks (June 2026)
| Risk | Description |
|---|---|
| Implicit trust | Agents treat MCP responses as authoritative system data |
| Event injection | Externally-influenced data (Sentry DSN, support tickets) becomes agent input |
| Prompt injection via MCP | Malicious servers craft prompts requesting LLM completions |
| Session hijacking | Stateful MCP connections vulnerable to replay/resume attacks |
| Covert tool invocation | Hidden tool calls without user awareness |
MCP sampling and tool responses create indirect prompt-injection vectors. Defense requires execution-layer controls, not prompt hardening alone.
Industry Impact
MCP is emerging as a potential standard for AI connectors:
- Enables “plug and play” AI integrations
- Reduces custom integration development effort
- Expands attack surface as more tools connect via MCP (agentjacking demonstrated at scale)
Key Points
- 2026-08-04: Referenced as integration standard in kiro-crew launch materials (2026-08-04-aws-kiro-crew-opensourceforu)