Agents inside Cursor, Claude, VS Codeuse your MCP through tools.
We show which tools connect across hosts, and which ones break,and what to fix first.
Cover your blind spots44K tools
Agents don't tell you the tool is broken.They pick another one.
You cannot prioritize the work.
Your tickets and your 200s do not say the agent finished the job. We tell you which tools did the work on hosts you do not run, so the roadmap is not a guess.
What to ship
fetch
Page title and first paragraph came back.
search
Came back. Not the work.
write
No run.
Just the MCP URL. No SDK needed.
Paste the server URL and auth. No SDK and no code change. Named hosts begin connecting.
Connect an MCP server
URL, auth, and the hosts we will connect as
URL
Check every
Hosts we check
Auth
Know which hosts can actually reach you.
Same server. Different hosts. We record whether each one can connect, list tools, and complete a call.
Your MCP Tools
Cursor
ReachableCatalog
Listed
Call
Failed
Claude
ReachableCatalog
Listed
Call
Worked
ChatGPT
ReachableCatalog
Fewer tools
Call
Not run
VS Code
BrokenCatalog
No catalog
Call
Not run
Prove which tools did the job.
Listed is not called. Called is not the work. We list, call, and score the job on those same hosts.
Per tool
fetch
Did the jobAnswer came back
No hidden error inside a 200
No auth or permission errors
Non-trivial payload
The page title and the first paragraph came back
Catch the step that killed the path.
Search, then fetch, then write. We walk that chain on the same MCP and stop where it breaks.
Do multi-step tool chains hold?
Connected workflow evidence
Enforcement open
- 1
Detected dependency
SEsearch→needs id→FEfetch→needs id→WRwrite - 2
Executed workflow
FailedSEsearchpassed→FEfetchfailed→WRwritenot reached - 3
Recommended for improved performance
Install
pip install agentstatus-mcpjobgraph
docsUse this path as the first graph to enforce.
Pin what broke after you shipped.
Compare catalogs, initialize results, and call verdicts across hosts, runs, and releases.
Day-by-day · Last 9 days (UTC)
Cooler = better for that row · Hotter = worse · Empty = no data that day
Your biggest blind spots sit outside your logs,inside hosts and paths you don't control.
We show what breaks before it hits your wire, and what to fix first.
Cover your blind spots