Repository navigation
feat(coinbase-mcp): add agent controls guidance for orders and payments - #21
Open
apmcdermott wants to merge 1 commit into
Open
apmcdermott wants to merge 1 commit into
apmcdermott wants to merge 1 commit into
Conversation
🟡 Heimdall Review Status
|
This branch has not been deployed
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Description
Coinbase MCP is adding
coinbase_agent_controls_get, a read-only tool that returns the user's agent spend limits (orders and x402 payments) and whether the user's automatic stop has paused the app. This adds guidance so agents check it before they preview an order or pay for research, instead of finding out from a refusal.references/trading.md: read the controls in step 1, stop onpause_status: yes, treatunknownas possibly paused, compare the order withmax(per order) orremaining(rolling), and remember the snapshot is advisory. Adds a row to the MCP tool table.references/x402.md: checkx402_paymentlimits and pause before paying.SKILL.md: a spend-limit or paused refusal is the user's control; don't split or reroute to get around it.All of it is conditional on the server exposing the tool, so it is safe to merge before the tool is live on
/mcpand/mcp/chatgpt.Change type
Validation
python3 -m unittest discover -s tests: 38 tests OK.python3 scripts/build-distributions.py: builds; the new guidance appears in the portable, Claude, Codex and ChatGPT packages, and ChatGPT still omitsx402.md.Not run: native harness loading or an authenticated smoke test. The tool is not live yet, so I could not check its exposed schema through
tools/list.Generated portable manifest and MCP config validate against the vendored Agent Plugins schemas
Package paths and skill references remain inside each generated plugin root
Marketplace, skills, MCP, and icon paths are valid
Exactly one canonical skill library; generated copies are not committed
Claude compatibility metadata/endpoint and marketplace sources agree with the portable package
Tool schemas, authorization, and retry behavior reviewed (field names match the tool's current contract; recheck against
tools/listonce it is live)README and changelog updated; versions consistent
No unapproved disclosures or sensitive data
Signed commits
Release considerations
Ship after the tool is live on the hosted MCP endpoints, or rely on the "where exposed" wording until then.