Delegated / attenuated authority for MCP agent tool calls
Nobody has claimed this yet.
Assessment
- Difficulty
- 5/5
- Estimated time
- Over a week
- Newbie friendliness
- 25/100
- Issue type
- Feature
- Clarity
- Needs clarification
- Activity status
- Quiet
- Tech stack
- python, typescript
- Domain
- authorization
Research direction
Start by reviewing the architectural question in this issue and the linked OAAF implementation. Compare the proposed delegated-authority profile with this repository’s existing MCP authorization extensions and governance process. Done would require maintainer agreement on whether this belongs here before a narrowly scoped proposal or PR can be defined.
Written by the indexing model from the issue text.
Description
I’m working on OAAF (Open Agent Authority Framework), an open interoperability framework for delegated authority across AI agents and tools.
We’ve implemented an MCP enforcement profile where delegated authority is verified before the normal MCP authorization/PDP path. The authority can be narrower than the underlying credential, so an agent with valid credentials can still be denied a tool call that wasn’t delegated to it.
For example:
Agent credential:
broad repository access
Delegated authority:
repo.read
repo.write
MCP tools/call:
repo.merge
OAAF authority precondition:
DENY
Downstream PDP/tool:
never invoked
The goal is specifically not to replace MCP authorization or introduce another competing credential format. OAAF profiles existing standards for delegated/attenuated authority and composes with the normal MCP authorization path.
We have a working TypeScript/Python implementation, MCP/COAZ binding, portable conformance corpus, and implementation-independent conformance runner:
OAAF: https://github.com/espradley/oaaf
Before proposing an extension or SEP, I’d appreciate maintainer feedback on the architectural question:
Does delegated/attenuated agent authority belong as an optional MCP authorization extension in this repository, or would maintainers prefer it remain an external interoperability profile layered ahead of MCP authorization?
If this is in scope here, I’d be happy to prepare a narrowly scoped proposal/PR following the project’s governance process.
- Dominant language
- MDX
- Stars
- 164
- Forks
- 54
- PR merge metrics
- No merged PRs in 30d
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
More from modelcontextprotocol/ext-auth
-
DEBUG Openbug
Difficulty 5/5 Over a week Newbie friendliness 10/100
-
enhancement
Difficulty 5/5 Over a week Newbie friendliness 30/100
modelcontextprotocol/ext-auth#26 · 1 comment ·
-
Difficulty 2/5 1-3 hours Newbie friendliness 35/100
-
enhancement
Difficulty 5/5 Over a week Newbie friendliness 25/100
modelcontextprotocol/ext-auth#21 · 1 comment ·
-
enhancement
Difficulty 5/5 Over a week Newbie friendliness 35/100
modelcontextprotocol/ext-auth#18 · 2 comments ·
All issues in modelcontextprotocol/ext-auth
Similar issues
-
blocklist removal
Difficulty 2/5 1-3 hours Newbie friendliness 65/100
MetaMask/eth-phishing-detect#296544 ·
-
Difficulty 2/5 1-3 hours Newbie friendliness 70/100
Azure/azure-functions-docker#1257 ·
-
area:proxy bug security severity:low track:open-source
Difficulty 2/5 1-3 hours Newbie friendliness 75/100
-
bug server
Difficulty 2/5 1-3 hours Newbie friendliness 70/100
-
Difficulty 2/5 1-3 hours Newbie friendliness 70/100
bytedance/UI-TARS-desktop#2009 · 1 comment ·