Agenda

The project's Antitrust Policy is linked from the LF and project websites. The policy is important when multiple companies, including potential industry competitors, are participating in meetings. Please review it, and if you have any questions, please contact your company’s legal counsel. Members of the LF may contact Andrew Updegrove at the firm Gesmer Updegrove LLP, which provides legal counsel to the LF.

• API Design Guide Enhancements

• Tool Definition Guide

• Security & Consent Guidance

References:

TSC: MCP Enablement Program – Phase 0

CAMARA + MCP Position Paper

Minutes

API Design Guide Enhancements

Improve API Design Guidelines for MCP/Agent readiness · Issue #587 · camaraproject/Commonalities

Position paper:

CAMARA's guidelines provide a solid foundation for consistent API design across the project.
Enhancements may be needed for optimal MCP integration. Examples may include making
parameter naming consistent across all APIs. This consistency facilitates automated MCP functions,
reducing manual mapping work. Furthermore, additional error responses may be needed to enhance
the reliability of AI interpretation. If an API call fails, AI systems require clear, consistent error
messages that they can understand and act upon.
Additionally, API documentation must evolve beyond technical specifications. Rich natural language
descriptions help AI systems understand what each API does and when to use it. Comprehensive
input/output examples demonstrate proper usage patterns, making it easier for AI to generate
correct API calls

@Kevin Smith mentioned RFC9727 - helps humans and agents to discover what APIs are available from a given publisher, and proposes a link set format API metadata could be annotated - worth to look from MCP perspective

@Ludovic Robert mentioned positive experiences from Orange for exposing CAMARA APIs with MCP: while API specifications provide necessary data, open issues are: user consent, and context information for AI agent.

Tool Definition Guide

Preparation of CAMARA MCP Tool Definition Guide · Issue #588 · camaraproject/Commonalities

Position paper:

Creating MCP function descriptions (“MCP tools”) for CAMARA APIs presents a crucial opportunity to
create industry-wide consistency. Rather than leaving interpretation to individual ecosystem players,
CAMARA may provide authoritative MCP function definitions as core deliverables alongside API
specifications.
This approach ensures consistency across implementations, significantly lowers barriers for AI
developers, and maintains quality control over how network capabilities are exposed to AI systems.
These CAMARA-defined descriptions should be versioned in lockstep with corresponding CAMARA API
specifications, ensuring synchronized evolution.

@Nick Venezia created CAMARA+API+to+MCP+Tool+Mapping while working on CAMARA + MCP Position Paper.

He also recommended MCP Inspector for disclosure of tool calls and authentication flows for agent workflows

@Jesús Peña García-Oliva raised a question about whether MCP tools should always be mapped to a specific CAMARA API, noting that operators might implement interfaces differently.

@Mark Cornall reminded that we should be looking at how do we use and make the CAMARA APIs exposed with MCP.

Security & Consent Guidance

CAMARA Security, Privacy, and Consent guidance for MCP · Issue #347 · camaraproject/IdentityAndConsentManagement

Position paper:

Security and Interoperability Considerations
While CAMARA's OAuth 2.0/OpenID Connect-based security profile aligns conceptually with MCP's
authorization framework, implementation challenges remain before MCP tools for CAMARA APIs can
be used in production networks. MCP implementations must manage authentication tokens for AI
systems. Three-Legged Access Tokens involve multiple steps across three parties: the user, the
application, and the authorization server. Because AI systems cannot participate directly in the OAuth
authentication flow, the MCP layer must handle this complexity. Extension of the CAMARA security
guidelines will be needed to ensure consistent security handling across MCP and CAMARA APIs. The
latest MCP specification introduces improvements to authorization flows but does not eliminate the
integration work required for alignment with CAMARA's security profile.
User consent
CAMARA's explicit purpose declaration requirements align well with MCP's transparency principles.
However, these declarations need seamless integration into how AI systems will make API calls. Most
critically, the MCP layer must abstract the complexities of consent management while maintaining full
compliance with CAMARA’s stringent requirements.

@Jesús Peña García-Oliva presented the issue #347 in ICM and the topics covered there.

AOB

Welcome to people bridging to MCP groups.

@Ludovic Robert offered more detailed presentation of implementation of MCP for CAMARA APIs.

Action items