Connects Claude to Wisepanel's multi-agent deliberation API, letting you run debates between Claude, Gemini, and Perplexity from your editor. You start a deliberation with a question and topology (small, medium, large panels), poll for streaming responses as each AI weighs in across multiple rounds, then optionally publish the finished debate to Wisepanel Commons for public sharing. Useful when you want diverse model perspectives on architecture decisions, content strategy, or research questions without manually switching between providers. The polling mechanism means you get real-time responses as the panel deliberates rather than waiting for everything to complete.
An MCP server that gives Claude Code and any MCP-compatible client direct access to Wisepanel's multi-agent deliberation platform.
Run deliberations across Claude, Gemini, and Perplexity. Stream panelist responses in real-time. Publish to the Wisepanel Commons.
Add to your MCP client config (e.g. ~/.mcp.json for Claude Code):
{
"mcpServers": {
"Wisepanel": {
"command": "npx",
"args": ["-y", "wisepanel-mcp"],
"env": {
"WISEPANEL_API_KEY": "your-api-key"
}
}
}
}
Get your API key at wisepanel.ai/settings.
wisepanel_startStart a deliberation. Convenes a panel of AI models to debate a question from assigned perspectives. Returns run_id immediately.
| Parameter | Type | Description |
|---|---|---|
question | string (required) | The topic for the panel to deliberate |
topology | string | Panel size: small (faster), medium (balanced), large (thorough) |
model_group | string | mixed (random), smart, fast, cheap, informed (search-augmented), large (largest context). Or single provider: openai, anthropic, google, perplexity |
rounds | number | Deliberation rounds (1-5). More rounds deepen the debate |
context | string | Additional framing context |
compression | string | Context compression: none, moderate, aggressive (default) |
short_responses | boolean | Request concise panelist responses |
wisepanel_pollLong-polls a running deliberation (waits up to 15s for new events). Returns panelist responses as they arrive.
wisepanel_resultRetrieve full results of a completed deliberation. Only needed if you didn't poll it live.
wisepanel_cancelCancel a running deliberation.
wisepanel_publishPublish a completed deliberation to the Wisepanel Commons. Makes it publicly viewable and shareable.
wisepanel_list_runsList all deliberation runs in the current session.
1. wisepanel_start -> returns run_id
2. wisepanel_poll -> (repeat) returns panelist responses as they arrive
3. On completion, poll includes publish_available: true
4. wisepanel_publish -> publishes to Commons, returns public URL
| Variable | Required | Description |
|---|---|---|
WISEPANEL_API_KEY | Yes | Your Wisepanel API key |
WISEPANEL_API_URL | No | API base URL (defaults to https://api.wisepanel.ai) |
git clone https://github.com/ikoskela/wisepanel-mcp.git
cd wisepanel-mcp
npm install
npm run dev
MIT
WISEPANEL_API_KEY*secretYour Wisepanel API key. Generate one at wisepanel.ai/settings.
WISEPANEL_API_URLAPI base URL. Defaults to https://api.wisepanel.ai
io.github.ericm1018/skillfm-llm-cost-optimizer-openai-anthropic-usage
io.github.mikerawsonnz/llm-orchestration-agent
io.github.mikerawsonnz/authenticated-llm-agent
labforgedev/copilot-memory-mcp
csoai-org/agent-prompt-injection-firewall-mcp
io.github.mikerawsonnz/authenticated-multi-llm-agent