Skip to content

Propose five Mission Contract enhancements from implementation experience#10

Open
nickgamb-strata wants to merge 2 commits into
dickhardt:mainfrom
nickgamb-strata:proposed-extensions/mission-contract-enhancements
Open

Propose five Mission Contract enhancements from implementation experience#10
nickgamb-strata wants to merge 2 commits into
dickhardt:mainfrom
nickgamb-strata:proposed-extensions/mission-contract-enhancements

Conversation

@nickgamb-strata
Copy link
Copy Markdown

@nickgamb-strata nickgamb-strata commented Apr 15, 2026

Summary

Based on our implementation of AAuth Mission Contracts for MCP (Model Context Protocol) tool governance, we identified five optional extensions that address gaps in the current Mission spec (Section 8). All proposals are backward-compatible and complement the existing design.

We originally built a "Desired Outcome Contract" (DOC) protocol for intent-bound authorization. After evaluating both approaches, we aligned with AAuth and migrated our POC to Mission Contracts. These proposals capture the novel concepts from DOC that proved valuable in practice.

Proposed Extensions

  1. Tamper-evident mission log via hash chaining — Each audit entry chains to the previous via SHA-256(prev_hash | action | params | result), seeded from the mission's s256. Addresses the lack of integrity mechanisms in the mission log (Section 8.3).

  2. Mission template discovery — Optional PS endpoint publishing structured mission templates that help agents compose better proposals. Reduces clarification rounds for first-time interactions.

  3. Mission constraint budgetsmax_tool_calls and timeout_seconds fields in the mission blob providing hard limits on agent execution, complementing contextual PS governance.

  4. Tool ordering constraintsrequired_predecessors and prohibited_sequences encoding domain safety rules (e.g., must read account before modifying it).

  5. Denial category classificationdenial_category field on permission responses distinguishing authorization_denied, intent_denied, and trajectory_denied for richer observability.

Reference Implementation

All five proposals are demonstrated in a working POC with a Person Server (Go), MCP Auth Proxy (Python), and Enterprise Ledger (banking MCP server with tools of varying sensitivity). The POC implements the complete AAuth mission flow: template discovery → mission proposal → HITL approval with s256 computation → per-call permission for non-pre-approved tools → hash-chained audit logging. Reference implementation available upon request.

Test plan

  • Review each proposal for compatibility with existing AAuth design principles
  • Verify proposals don't conflict with planned companion specifications (Section 8.5)
  • Consider whether any proposals should be normative vs. informational

…perience

Based on our implementation of intent-bound authorization for MCP tool
governance, these proposals address gaps in the Mission Contract spec:

1. Tamper-evident mission log via hash chaining (audit entries)
2. Mission template discovery (PS endpoint for structured templates)
3. Mission constraint budgets (max_tool_calls, timeout_seconds)
4. Tool ordering constraints (required_predecessors, prohibited_sequences)
5. Denial category classification (authorization/intent/trajectory)

All proposals are OPTIONAL extensions that complement the existing design.
Reference implementation available upon request.
@nickgamb-strata nickgamb-strata force-pushed the proposed-extensions/mission-contract-enhancements branch from 65845ee to 22f2a11 Compare April 16, 2026 00:10
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant