add-mcscopilot — Claude Code skill: what it does, how to install
add-mcscopilot attaches the Microsoft Copilot Studio connector to Power Apps code apps, configures agent invocation, and handles responses.
MIT ★ 1,167 updated 2026-10-29
/plugin marketplace add microsoft/power-platform-skills
/plugin install code-apps-preview@power-platform-skillsWhat add-mcscopilot does
This skill integrates Copilot Studio agents directly into Power Apps code projects. It resolves connection IDs via /list-connections or links you to the Power Apps maker portal, running pa app add data-source --connector microsoftcopilotstudio -c <connection-id> to add the source.
You must publish the agent in Copilot Studio channels beforehand. The skill enforces ExecuteCopilotAsyncV2 for code generation because the standard ExecuteCopilotAsync endpoint fails with 502 errors and /execute omits payload responses.
After setting up client calls, it executes npm run build to catch TypeScript errors and logs progress into memory-bank.md.
What it helps with
- add Microsoft Copilot Studio connector to Power Apps
- invoke Copilot Studio bots synchronously using ExecuteCopilotAsyncV2
- extract structured JSON output from agent responses
- catch TypeScript build errors after connector generation
Example prompts for the agent
- Add the Microsoft Copilot Studio connector to my Power Apps project
- Configure an agent call via ExecuteCopilotAsyncV2 and parse its JSON response
- Run add-mcscopilot to bind the cr3e1_myAgent bot to this code app
How to install add-mcscopilot
1Plugin marketplace
/plugin marketplace add microsoft/power-platform-skills/plugin install code-apps-preview@power-platform-skillsThis installs the whole code-apps-preview plugin with all its skills
2Skills CLI (Vercel)
npx skills add microsoft/power-platform-skills --skill add-mcscopilot -a claude-code3Manually: put the files in place
~/.claude/skills/add-mcscopilot/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/add-mcscopilot/
1Skills CLI (Vercel)
npx skills add microsoft/power-platform-skills --skill add-mcscopilot -a codex2Manually: put the files in place
.agents/skills/add-mcscopilot/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add microsoft/power-platform-skills --skill add-mcscopilot -a cursor2Manually: put the files in place
.cursor/skills/add-mcscopilot/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install microsoft/power-platform-skills plugins/code-apps/skills/add-mcscopilot2Manually: put the files in place
.github/skills/add-mcscopilot/SKILL.md1Skills CLI (Vercel)
npx skills add microsoft/power-platform-skills --skill add-mcscopilot -a gemini-cli2Platform CLI
gemini skills install https://github.com/microsoft/power-platform-skills --path plugins/code-apps/skills/add-mcscopilotManually: put the files in place
.devin/skills/add-mcscopilot/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about add-mcscopilot
How to install add-mcscopilot in Claude Code?
Run both marketplace commands in order: /plugin marketplace add microsoft/power-platform-skills and /plugin install code-apps-preview@power-platform-skills.
What does add-mcscopilot do?
It registers the Copilot Studio data source in your Power Apps code app via pa app and writes typed service code to query published agents.
Why does it specifically use ExecuteCopilotAsyncV2?
Alternative endpoints fail: /executeAsync throws 502 Bad Gateway responses, while /execute only returns a conversation ID without the agent response.
Source text
SKILL.md · MIT
---
name: add-mcscopilot
description: Adds Microsoft Copilot Studio connector to a Power Apps code app. Use when invoking Copilot Studio agents, sending prompts to agents, or integrating agent responses.
user-invocable: true
allowed-tools: Read, Edit, Write, Grep, Glob, Bash, LSP, TaskCreate, TaskUpdate, TaskList, TaskGet, AskUserQuestion, Skill
model: sonnet
---
**📋 Shared Instructions: [shared-instructions.md](${PLUGIN_ROOT}/shared/shared-instructions.md)** - Cross-cutting concerns.
# Add Microsoft Copilot Studio
## Workflow
1. Check Memory Bank → 2. Add Connector → 3. Configure → 4. Build → 5. Update Memory Bank
---
### Step 1: Check Memory Bank
Check for `memory-bank.md` per [shared-instructions.md](${PLUGIN_ROOT}/shared/shared-instructions.md).
### Step 2: Add Connector
**First, find the connection ID** (see [connector-reference.md](${PLUGIN_ROOT}/shared/connector-reference.md)):
Run the `/list-connections` skill. Find the Microsoft Copilot Studio connection in the output. If none exists, direct the user to create one using the environment-specific Connections URL — construct it from the active environment ID in context (from `power.config.json` or a prior step): `https://make.powerapps.com/environments/<environment-id>/connections` → **+ New connection** → search for the connector → Create.
```bash
pa app add data-source --connector microsoftcopilotstudio -c <connection-id>
```
### Step 3: Configure
Ask the user which Copilot Studio agent they want to invoke and what operations they need.
**Agent Setup Prerequisites** (manual steps the user must complete in Copilot Studio):
1. **Publish the agent**: In Copilot Studio, click Channels → select Teams → add to Teams → click Publish.
2. **Get the agent name**: Under Channels, click "Web app". The connection string URL contains the agent name. Example: `https://...api.powerplatform.com/copilotstudio/dataverse-backed/authenticated/bots/cr3e1_myAgent/conversations?...` — the agent name is `cr3e1_myAgent`.
**ExecuteCopilotAsyncV2** -- execute an agent and wait for the response:
Use the `ExecuteCopilotAsyncV2` operation (path: `/proactivecopilot/executeAsyncV2`). This is the **only** endpoint that reliably returns agent responses synchronously. It is the same endpoint used by Power Automate's "Execute Agent and wait" action.
```typescript
const result = await MicrosoftCopilotStudioService.ExecuteCopilotAsyncV2({
message: "Your prompt or data here", // Can be a JSON string
notificationUrl: "https://notificationurlplaceholder" // Required by API but unused; any URL works
});
// Response structure:
// result.responses — Array of response strings from the agent
// result.conversationId — The conversation ID
// result.lastResponse — The last response from the agent
// result.completed — Boolean indicating if the agent finished
```
**Important:** Agents often return responses as JSON strings. Parse the `responses` array to extract meaningful data:
```typescript
const agentResponse = result.responses?.[0];
if (agentResponse) {
const parsed = JSON.parse(agentResponse);
// Extract specific fields, e.g., parsed.trend_summary
}
```
Use `Grep` to find specific methods in the generated service file (generated files can be very large — see [connector-reference.md](${PLUGIN_ROOT}/shared/connector-reference.md#inspecting-large-generated-files)).
#### Known Issues
- **ExecuteCopilot** (`/execute`) -- fire-and-forget, only returns `ConversationId`, not the actual response. Do NOT use this.
- **ExecuteCopilotAsync** (`/executeAsync`) -- returns 502 "Cannot read server response" errors. Do NOT use this.
- **Conversation turn model** (`/conversations/{ConversationId}`) -- only works after `/execute`, which doesn't provide responses. Do NOT use this.
- **Response casing varies** -- check all variations: `conversationId`, `ConversationId`, `conversationID`.
### Step 4: Build
```bash
npm run build
```
Fix TypeScript errors before proceeding. Do NOT deploy yet.
### Step 5: Update Memory Bank
Update `memory-bank.md` with: connector added, agent name configured, configured operations, build status.
© Microsoft · MIT · microsoft/power-platform-skills