mcp-batch-research

Name: mcp-batch-research
Author: wheattoast11

Run multiple queries in parallel. Max 10.

by wheattoast11(0) 0 installs

Free

Free account. Installing gives you the manifest plus copy-paste snippets.

See reviews

About

Prompt file imported from wheattoast11/openrouter-deep-research-mcp (.claude/commands/mcp-batch-research.md). Fill in {{arguments}} before use. Copyright stays with the author.

MCP Batch Research

Run multiple queries in parallel. Max 10.

Steps

Parse topics (comma/newline separated)
batch_research({ queries: [...], waitForCompletion: true })
Extract reportIds from result
get_report({ reportId }) for each
Compare findings

Options

Param	Default	Description
waitForCompletion	true	Block until all complete
costPreference	"low"	"low" or "high"
timeoutMs	300000	5 min max wait

Example

Input: "AI safety, quantum computing, climate tech" -> queries: ["AI safety", "quantum computing", "climate tech"]

Topics

Use it

Copy one of these into your project. Installing also returns the manifest and these snippets.

# MCP Batch Research

Run multiple queries in parallel. Max 10.

## Steps

1. Parse topics (comma/newline separated)
2. `batch_research({ queries: [...], waitForCompletion: true })`
3. Extract `reportIds` from result
4. `get_report({ reportId })` for each
5. Compare findings

## Options

| Param | Default | Description |
|-------|---------|-------------|
| waitForCompletion | true | Block until all complete |
| costPreference | "low" | "low" or "high" |
| timeoutMs | 300000 | 5 min max wait |

## Example

Input: "AI safety, quantum computing, climate tech"
-> queries: ["AI safety", "quantum computing", "climate tech"]

## Topics
{{arguments}}

Installed into a catalogue, chosen by a router

Install mcp-batch-research and it becomes one more candidate the router can pick - when it fits.

A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.

Photo: RDNE Stock project

Manifest

The prompt text and its fill-in variables. Copy it or fetch it by URL from your own code.

wheattoast11-openrouter-deep-research-mcp-mcp-batch-rese-888584.prompt.jsonjson

{
  "prompt": "# MCP Batch Research\n\nRun multiple queries in parallel. Max 10.\n\n## Steps\n\n1. Parse topics (comma/newline separated)\n2. `batch_research({ queries: [...], waitForCompletion: true })`\n3. Extract `reportIds` from result\n4. `get_report({ reportId })` for each\n5. Compare findings\n\n## Options\n\n| Param | Default | Description |\n|-------|---------|-------------|\n| waitForCompletion | true | Block until all complete |\n| costPreference | \"low\" | \"low\" or \"high\" |\n| timeoutMs | 300000 | 5 min max wait |\n\n## Example\n\nInput: \"AI safety, quantum computing, climate tech\"\n-> queries: [\"AI safety\", \"quantum computing\", \"climate tech\"]\n\n## Topics\n{{arguments}}",
  "variables": [
    "arguments"
  ],
  "notes": "Run multiple queries in parallel. Max 10.",
  "metadata": {
    "source": {
      "provider": "github-claude-commands",
      "repository": "https://github.com/wheattoast11/openrouter-deep-research-mcp",
      "path": ".claude/commands/mcp-batch-research.md",
      "ref": "1506d9f5a77736eed306c7f47065cfefbf85b5ed",
      "url": "https://github.com/wheattoast11/openrouter-deep-research-mcp/blob/1506d9f5a77736eed306c7f47065cfefbf85b5ed/.claude/commands/mcp-batch-research.md",
      "key": "wheattoast11/openrouter-deep-research-mcp/.claude/commands/mcp-batch-research.md"
    }
  }
}

Fetch it by URL: GET /api/v1/registry/wheattoast11-openrouter-deep-research-mcp-mcp-batch-rese-888584/manifest?version=1.0.0