Search / io.github.cristianmoroaica/bountyverdict
Read-only GitHub bounty, agent harness, Actions failure, flake, and MCP tool-drift decisions.
v1.1.1 · active · repository · website · descriptor JSON · versions
protogrid{
"mcpServers": {
"bountyverdict": {
"type": "http",
"url": "https://bountyverdict-agent-production.mimirslab.workers.dev/mcp"
}
}
}claude mcp add --transport http bountyverdict https://bountyverdict-agent-production.mimirslab.workers.dev/mcp[mcp_servers.bountyverdict]
url = "https://bountyverdict-agent-production.mimirslab.workers.dev/mcp"
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"bountyverdict": {
"type": "remote",
"url": "https://bountyverdict-agent-production.mimirslab.workers.dev/mcp",
"enabled": true
}
}
}{
"mcpServers": {
"bountyverdict": {
"type": "http",
"url": "https://bountyverdict-agent-production.mimirslab.workers.dev/mcp"
}
},
"deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=bountyverdict&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vYm91bnR5dmVyZGljdC1hZ2VudC1wcm9kdWN0aW9uLm1pbWlyc2xhYi53b3JrZXJzLmRldi9tY3AifQ%3D%3D"
}{
"servers": {
"bountyverdict": {
"type": "http",
"url": "https://bountyverdict-agent-production.mimirslab.workers.dev/mcp"
}
}
}{
"mcpServers": {
"bountyverdict": {
"httpUrl": "https://bountyverdict-agent-production.mimirslab.workers.dev/mcp"
}
}
}extensions:
"bountyverdict":
enabled: true
name: "bountyverdict"
type: streamable_http
uri: "https://bountyverdict-agent-production.mimirslab.workers.dev/mcp"
timeout: 300
Not scored: fewer than three checks apply, usually because no remote answered a credential-free probe or the server is a local package.
protocol.modern, protocol.stateless, protocol.transport, protocol.list_ttlno remote answered a protocol handshake (not probed yet, unreachable, or local-only)auth.prm, auth.as_metadata, auth.cimdno remote uses OAuthauth.secret_in_urlno templated URLtools.descriptions, tools.description_length, tools.schemas, tools.annotations, tools.directory_hints, tools.token_cost, tools.api_dumptool list unknown (behind auth, not probed, or empty)stability.changes, stability.rug_pulltool list unknowndeps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI packageNo tool definition changes recorded. A server's first observation is its baseline; later probes record what changes.
Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.
+repository +namespace-matches-repo +website -unreachable(13 failures) ~updated-90d-ago
Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.
| remote | auth | reachable | uptime 30d | p50 | protocol | last ok |
|---|---|---|---|---|---|---|
https://bountyverdict-agent-production.mimirslab.workers.dev/mcp streamable-http | unknown | no (13 failures) | 0% | – | – | – |
No tools observed. Tools appear once a credential-free probe can list them.
Schemas: list_tools.
{
"name": "io.github.cristianmoroaica/bountyverdict",
"_meta": {
"io.modelcontextprotocol.registry/publisher-provided": {
"tools": [
{
"name": "check_github_bounty",
"task": "Assess one bounty's claimability and delivery risk",
"price": "$0.05 USDC",
"returns": "AVOID, CAUTION, or VIABLE with evidence and reuse guidance"
},
{
"name": "rank_github_bounties",
"task": "Choose the best of 2-10 bounty issues",
"price": "$0.40 USDC",
"returns": "Ranked verdicts, best candidate, partial failures, and reuse guidance"
},
{
"name": "audit_agent_harness",
"task": "Audit coding-agent repository instructions",
"price": "$0.03 USDC",
"returns": "READY, REVIEW, or REPAIR with commit-pinned findings"
},
{
"name": "diagnose_github_actions_run",
"task": "Find why a GitHub Actions run failed",
"price": "$0.04 USDC",
"returns": "Root-cause verdict, redacted evidence, and next actions"
},
{
"name": "classify_github_actions_flake",
"task": "Decide whether to retry once or fix",
"price": "$0.07 USDC",
"returns": "Flake verdict and ONCE, NO, or NOT_NEEDED retry action"
},
{
"name": "check_mcp_tool_drift",
"task": "Detect breaking MCP tool-catalog changes",
"price": "$0.02 USDC",
"returns": "Compatibility verdict, accept or block action, and exact hashes"
}
],
"keywords": [
"GitHub bounty",
"open source bounty",
"bounty claimability",
"GitHub Actions failure",
"CI failure diagnosis",
"flaky workflow retry",
"coding agent instructions",
"AGENTS.md audit",
"MCP tools/list",
"MCP schema drift",
"agent tool compatibility",
"x402"
],
"useCases": [
"Check one public GitHub bounty before coding",
"Rank 2-10 public GitHub bounty opportunities",
"Audit repository instructions before assigning a coding agent",
"Find the root cause of a failed public GitHub Actions run",
"Decide whether a failed Actions run should be retried once or fixed",
"Gate an MCP tools/list update for compatibility and safety regressions"
],
"categories": [
"developer-tools",
"github",
"continuous-integration",
"agent-safety",
"commerce"
],
"documentation": "https://cristianmoroaica.github.io/bountyverdict/"
}
},
"icons": [
{
"src": "https://cristianmoroaica.github.io/bountyverdict/favicon.svg",
"sizes": [
"any"
],
"mimeType": "image/svg+xml"
}
],
"title": "BountyVerdict Agent Decision Tools",
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
"remotes": [
{
"url": "https://bountyverdict-agent-production.mimirslab.workers.dev/mcp",
"type": "streamable-http"
}
],
"version": "1.1.1",
"repository": {
"url": "https://github.com/cristianmoroaica/bountyverdict",
"source": "github"
},
"websiteUrl": "https://cristianmoroaica.github.io/bountyverdict/",
"description": "Read-only GitHub bounty, agent harness, Actions failure, flake, and MCP tool-drift decisions."
}