Agents and fan-out

bridge ask is a stable, non-interactive surface for scripts and agents: it prints to stdout, never prompts in a pipe, and --json emits a machine-readable payload.

# one provider
bridge ask --provider claude --json "summarize the tradeoffs of optimistic locking"

# fan out across several free chats; one call, replies keyed by provider
bridge ask --provider claude,deepseek,grok --json "same question, three models"
# → { "claude": { "ok": true, "reply": "…", "elapsedMs": 8123 },
#     "deepseek": { "ok": true, "reply": "…", "elapsedMs": 6210 },
#     "grok": { "ok": false, "error": "…", "elapsedMs": 300000 } }

Fan-out is partial-failure tolerant: the run exits non-zero only when every provider fails, or, with --strict, when any fails. Run bridge chrome start --provider <name> and sign in if needed; the bridge reuses the shared bridge Chrome profile across repos.

The bridge serve MCP server

The same fan-out core is exposed through outbound MCP tools. Launch a stdio MCP server with bridge serve and any MCP-capable agent can call ask({ prompt, providers }) or search_conversations({ query, providers, limit }) as native tools instead of shelling out. Register it with Claude Code:

claude mcp add ai-browser-bridge -- bridge serve

...or add it to any MCP client config directly (the standard stdio-server shape):

{
  "mcpServers": {
    "ai-browser-bridge": { "command": "bridge", "args": ["serve"] }
  }
}

The ask tool takes { prompt, providers?, timeoutSeconds? } and returns each provider's reply keyed by id (the same partial-failure-tolerant fan-out as bridge ask). The search_conversations tool takes { query, providers?, limit? } and returns matching conversation URLs keyed by provider. Run bridge chrome start --provider <name> first, so the gateway has a signed-in Chrome session to drive. This is the opposite direction to the inbound MCP server, which exposes your repo tools to the web model. See the full tool list.

Provider adapters other than ChatGPT and Gemini ship with best-effort selectors marked LIVE-VERIFY. Confirm them against the live signed-in site before relying on them in production.