protogrid

Search / io.github.maebsy/72hours

72hours security check

not classified

Scan a public GitHub repo, explain risks, get fix prompts and rescan to confirm fixes.

v1.1.0 · active · repository · descriptor JSON · versions

Not classified yet.The remote endpoints have not been probed successfully, or the listing has nothing to connect to.
Quality85new
Trust69of 100
Uptime, 30 days92%
Latency p50546 ms

Connect

8 clients · secrets stay placeholders
{
  "mcpServers": {
    "72hours": {
      "type": "http",
      "url": "https://oboe-handiness-enroll.ngrok-free.dev/mcp/service/rpc"
    }
  }
}
claude mcp add --transport http 72hours https://oboe-handiness-enroll.ngrok-free.dev/mcp/service/rpc
[mcp_servers.72hours]
url = "https://oboe-handiness-enroll.ngrok-free.dev/mcp/service/rpc"
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "72hours": {
      "type": "remote",
      "url": "https://oboe-handiness-enroll.ngrok-free.dev/mcp/service/rpc",
      "enabled": true
    }
  }
}
{
  "mcpServers": {
    "72hours": {
      "type": "http",
      "url": "https://oboe-handiness-enroll.ngrok-free.dev/mcp/service/rpc"
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=72hours&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vb2JvZS1oYW5kaW5lc3MtZW5yb2xsLm5ncm9rLWZyZWUuZGV2L21jcC9zZXJ2aWNlL3JwYyJ9"
}
{
  "servers": {
    "72hours": {
      "type": "http",
      "url": "https://oboe-handiness-enroll.ngrok-free.dev/mcp/service/rpc"
    }
  }
}
{
  "mcpServers": {
    "72hours": {
      "httpUrl": "https://oboe-handiness-enroll.ngrok-free.dev/mcp/service/rpc"
    }
  }
}
extensions:
  "72hours":
    enabled: true
    name: "72hours"
    type: streamable_http
    uri: "https://oboe-handiness-enroll.ngrok-free.dev/mcp/service/rpc"
    timeout: 300

Quality 85 / 100new

protocol75 · weight 25
  • warn
    protocol.modernnewest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
  • n/a
    protocol.statelessonly applies to 2026-07-28 servers
  • pass
    protocol.transportstreamable HTTP
  • n/a
    protocol.list_ttlonly applies to 2026-07-28 servers
authorizationn/a · weight 15
  • n/a
    auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
  • n/a
    auth.secret_in_urlno templated URL
tool hygiene93 · weight 30
  • pass
    tools.descriptionsevery tool has a description
  • pass
    tools.description_lengthdescriptions are concise
  • pass
    tools.schemasevery tool has an object input schema
  • pass
    tools.annotations15 of 15 tools declare readOnlyHint or destructiveHint
  • warn
    tools.directory_hints14 of 15 tools declare all four hints; missing: close_workspace (idempotentHint)
  • pass
    tools.token_costabout 1,873 tokens to load every tool
  • pass
    tools.api_dumptools are not a one-to-one API dump
stabilityn/a · weight 15
  • n/a
    stability.changes, stability.rug_pulltool history recorded for 6 of the 7 days needed
dependenciesn/a · weight 15
  • n/a
    deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

15 tools, about 1,873 tokens to load them all · tool set dbcc49057e69 · checked 2026-11-07 18:01 UTC

Tool changes

No 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.

Trust 69 / 100

provenance80
liveness17
freshness100
hygiene100

+repository +namespace-matches-repo -unreachable(2 failures) +updated-7d-ago

Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.

Endpoints

remoteauthreachableuptime 30dp50protocollast ok
https://oboe-handiness-enroll.ngrok-free.dev/mcp/service/rpc streamable-httpnoneno (2 failures)92%546 ms2025-11-252026-11-06

Tools (15)

audit_repositoryOne call security audit of a PUBLIC GitHub repo the user is authorized to scan. Creates a workspace if workspace_token is empty (keep the returned token private), scans, waits up to 90 s, starts GPU analysis for the top max_analyses (0-5) findings and returns summary + next steps. Reuse request_id only for the SAME request.
audit_statusread-onlyScan summary, analysis statuses and which fix prompts (get_fix_prompt) are ready, in one call.
check_fixAfter fixes are PUSHED to the default branch: rescan the same repo against scan_id and list resolved, persisting, new and key-reissue-needed findings. Same commit means the fix was not pushed yet.
close_workspacedestructiveRevoke this workspace and its result access. Does not cancel already submitted backend jobs.
create_workspaceCreate a private, expiring workspace. Save its capability only in the user's AI conversation.
generate_reportread-onlyGenerate the service's report from owned server scan and available analyses, indicating incomplete work.
get_analysisread-onlyPoll GPU status and delivery gates; inference can take several minutes. Never fake ready results.
get_fix_promptread-onlyGet a gated real LLM proposal. Agent must inspect code, check repo/commit, fix and test in its workspace.
get_scanread-onlyPoll every >=10 seconds; on done return actual commit, coverage and up to 50 LLM-input findings.
incident_reportread-onlyDraft only; NEVER submits. kind: assess/incident-24h/privacy-72h. incident requires discovered_at ISO time; optional organization {name,service_name,contact_email}, summary, incident_types, damage, actions_taken, personal_info {leaked: confirmed/suspected/none, affected_count, items}. Use only user-confirmed facts.
rescanRescan the SAME repository default branch. Only published changes are visible; unpushed edits are not.
service_inforead-onlyLearn the whole workflow and available service capabilities before creating work.
start_analysisStart GPU Red/Blue review of one real scan finding. Same inputs deduplicate.
start_scanStart a REAL public GitHub scan. User authorization required. Reuse request_id on identical retries.
verify_demoRuntime proof on the DEMO target only: isolated sandbox replays attacks before/after the fix and runs functional tests. mode: reference (human fix) or ai (Red/Blue generated attacks and fix). Not the user's repo. If a previous call returned status queued/running, pass its verify_job_id to keep polling the same job.

Schemas: list_tools.

Similar MCP servers

Official server.json
{
  "name": "io.github.maebsy/72hours",
  "title": "72hours security check",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://oboe-handiness-enroll.ngrok-free.dev/mcp/service/rpc",
      "type": "streamable-http"
    }
  ],
  "version": "1.1.0",
  "repository": {
    "url": "https://github.com/maebsy/YMCA-hackathon-2026",
    "source": "github",
    "subfolder": "integrations/mcp-handoff"
  },
  "description": "Scan a public GitHub repo, explain risks, get fix prompts and rescan to confirm fixes."
}