About Copilot Studio MCP
Copilot Studio MCP is an MCP server published by jgt87 in the Science category: build, test, ship and maintain Microsoft Copilot Studio agents from the editor.
Recent commit activity is the strongest signal that reported issues will get attention.
Install
Claude Code
claude mcp add copilot-studio-mcp -- npx -y copilot-studio-mcpnpx
npx -y copilot-studio-mcpThis server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Tools (3)
cs_analyze_flow_health*It fails sometimes.* Failure rate, duration median and 90th percentile, and which actions the failures land on. One action responsible for most of them is a broken step; failures spread across many point at the connection, throttling or the system being called.
Parameters not published.
cs_compare_flow_runs*It worked yesterday.* Diffs the failed run against the most recent successful one and names the action where they part company. With `compareTriggerData: true` it reports which keys of the trigger payload differ (key names only, never the values), which is what separates a bad input from a broken flow. Actions present in one run but not the other mean the definition itself changed.
Parameters not published.
cs_explain_flow_run*Why did this run fail?* A failed connector action carries no error message of its own - the message is in the action's outputs, behind a link that expires after a few days - so this fetches it, says whether the fault is the connector, an expression or a timeout, and shows the inputs the action was called with next to the outputs of the actions that ran just before it.
Parameters not published.
Ask AI
✦
Ask AI about Copilot Studio MCP
Powered by Claude · Grounded in docs
I know everything about Copilot Studio MCP. Ask me about installation, configuration, usage, or troubleshooting.
Security checks
6 checks have not been run yet.
Releases
v0.1.7v0.1.7 - preview · 14 Sep 2026A behaviour release, and the one change everybody notices: the tools that edit an agent no longer write on the first call. They return the change - a new file in full, an edit as a diff, instructions with their character count - and write…
v0.1.6v0.1.6 - flows · 11 Sep 2026A feature release about cloud flows, and about whether your model picks the right tool at all. Upgrade if you build Power Automate flows behind your agents, if you deploy solutions and keep having to bind connections by hand, or if you run…
v0.1.5v0.1.5 - registry · 10 Sep 2026Distribution release. Nothing in the server changed; upgrade only if you want the install path that does not involve a clone, or you found the package through a registry. Added Install from npm, without a clone. `npx -y…
v0.1.4v0.1.4 - attribution · 10 Sep 2026Testing and documentation release. Upgrade if you use `cs_run_conversation_tests` or `cs_chat` and want to know whether the agent actually called its tool, or if you read the README to find your way around. Added A conversation test can…
v0.1.3v0.1.3 - resilience · 10 Sep 2026Resilience release, for the two ways a long chat used to fail and the one way any cloud call did. Found by comparing this server's chat path against…