Index / MCP servers / Batchloom Evidence

Batchloom Evidence MCP server

Batchloom Evidence is an MCP server with 11 tools an agent can call, among them audit_report_citations, compare_evidence_snapshots, get_evidence_contract. It answers at https://batchloom-studio-0913.xuikatwsicrdsidm.chatgpt.site/v1/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 5 of 5 times since 14 September 2026; the last check, on 24 October 2026, succeeded.

Status
Answering
Tools
11
Official
yes, served from chatgpt.site
Reliability
5 of 5 checks
Response time
209 ms
Transport
streamable HTTP
Last checked
24 October 2026

Free citation-request checks, samples and snapshot comparison; paid evidence via a separate API.

Description as the publisher wrote it.

The 11 tools Batchloom Evidence offers

ToolWhat it does
audit_report_citationsFree deterministic audit of caller-supplied report text and structured references using [cite:id] markers. Lists unmarked text blocks, unknown/unused refs, duplicate exact source URLs, missing/unsupported URLs and quote presence in the repo
Inputs: report, references
compare_evidence_snapshotsCompare two supplied evidence snapshots bound to the same input. No fetch, payment or content storage. Unreadable sources and changed/unknown processing profiles are not classified as quote removal. Maximum 196608 bytes; no authenticity or
Inputs: input, before, after
get_evidence_contractRead price, exact supported hosts, limitations and safe purchase recovery. No network crawl or payment.
get_evidence_sampleRead a fixed synthetic evidence example. No live fetch, payment or truth guarantee.
get_manifestRead the free product manifest, source-license price, endpoint limits and purchase/recovery instructions. Does not buy or sign anything.
get_sampleRead three free fixed SVG examples. No source toolkit is included.
prepare_evidence_requestValidate input, compute its canonical hash and read exact payment/client requirements and receipt storage readiness. Fetches no source, generates no secret, signs and pays nothing. Source/facilitator capacity remains unchecked.
Inputs: requireAllSources, sources
preview_assetsRender one product as up to three SVG assets for free. Arguments are the render input directly, not an input wrapper; maximum 8192 UTF-8 bytes when serialized. Returns assets and warnings, without toolkit source.
Inputs: brand, products, formats, theme, style
trial_evidenceTry one supported source and one quote with the production extractor. No payment or durable receipt. Shared free quota plus 2 attempts/client/UTC day and 100 attempts/service/UTC day.
Inputs: requireAllSources, sources
validate_batchValidate up to 100 products and 3 formats for free. Arguments are the render input directly. Returns validity, product count, expected asset count and validation warnings; no rendered assets or toolkit source.
Inputs: brand, products, formats, theme, style
validate_evidence_requestCheck bounded URLs and literal quotes against the fixed host list before purchase. Does not fetch pages or establish source availability. No payment.
Inputs: requireAllSources, sources

Add Batchloom Evidence to your AI client

Every block below points at https://batchloom-studio-0913.xuikatwsicrdsidm.chatgpt.site/v1/mcp. Pick your client and copy.

Claude Code: one command in your terminal
claude mcp add --transport http batchloom-evidence https://batchloom-studio-0913.xuikatwsicrdsidm.chatgpt.site/v1/mcp
Claude Desktop: claude_desktop_config.json
{
  "mcpServers": {
    "batchloom-evidence": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://batchloom-studio-0913.xuikatwsicrdsidm.chatgpt.site/v1/mcp"]
    }
  }
}
Cursor: ~/.cursor/mcp.json, or .cursor/mcp.json in a project
{
  "mcpServers": {
    "batchloom-evidence": {
      "url": "https://batchloom-studio-0913.xuikatwsicrdsidm.chatgpt.site/v1/mcp"
    }
  }
}
VS Code and GitHub Copilot: .vscode/mcp.json
{
  "servers": {
    "batchloom-evidence": {
      "type": "http",
      "url": "https://batchloom-studio-0913.xuikatwsicrdsidm.chatgpt.site/v1/mcp"
    }
  }
}
Zed: Zed settings.json
{
  "context_servers": {
    "batchloom-evidence": {
      "url": "https://batchloom-studio-0913.xuikatwsicrdsidm.chatgpt.site/v1/mcp"
    }
  }
}
Windsurf: ~/.codeium/mcp_config.json
{
  "mcpServers": {
    "batchloom-evidence": {
      "serverUrl": "https://batchloom-studio-0913.xuikatwsicrdsidm.chatgpt.site/v1/mcp"
    }
  }
}
JetBrains AI Assistant: Settings, Tools, AI Assistant, MCP, New MCP Server, as JSON
{
  "mcpServers": {
    "batchloom-evidence": {
      "url": "https://batchloom-studio-0913.xuikatwsicrdsidm.chatgpt.site/v1/mcp"
    }
  }
}
Continue: .continue/mcpServers/neuronto.yaml
name: Batchloom Evidence
version: 0.0.1
schema: v1
mcpServers:
  - name: Batchloom Evidence
    type: streamable-http
    url: https://batchloom-studio-0913.xuikatwsicrdsidm.chatgpt.site/v1/mcp
Gemini CLI: ~/.gemini/settings.json
{
  "mcpServers": {
    "batchloom-evidence": {
      "httpUrl": "https://batchloom-studio-0913.xuikatwsicrdsidm.chatgpt.site/v1/mcp"
    }
  }
}
Codex CLI: MCP server config
{
  "mcpServers": {
    "batchloom-evidence": {
      "type": "http",
      "url": "https://batchloom-studio-0913.xuikatwsicrdsidm.chatgpt.site/v1/mcp"
    }
  }
}
Warp: MCP servers, + Add, paste JSON
{
  "mcpServers": {
    "batchloom-evidence": {
      "url": "https://batchloom-studio-0913.xuikatwsicrdsidm.chatgpt.site/v1/mcp"
    }
  }
}
Goose: a one-click extension link
goose://extension?url=https%3A%2F%2Fbatchloom-studio-0913.xuikatwsicrdsidm.chatgpt.site%2Fv1%2Fmcp&type=streamable_http&id=batchloom-evidence&name=Batchloom%20Evidence

Is Batchloom Evidence up right now?

It answered our last check on 24 October 2026 in 209 ms. Over 5 checks since 14 September 2026 it answered 5. Status here comes from Neuronto's own probes, not from the publisher.

MCP servers similar to Batchloom Evidence

Questions about Batchloom Evidence

Is there an official Batchloom Evidence MCP server?

Yes. It is published by chatgpt.site and served from batchloom-studio-0913.xuikatwsicrdsidm.chatgpt.site, the vendor's own domain: https://batchloom-studio-0913.xuikatwsicrdsidm.chatgpt.site/v1/mcp.

How many tools does Batchloom Evidence have?

11, as returned by the server's own tools/list on 24 September 2026: audit_report_citations, compare_evidence_snapshots, get_evidence_contract, get_evidence_sample, get_manifest, get_sample, prepare_evidence_request, preview_assets, and 3 more.

Is Batchloom Evidence down?

It answered our last check on 24 October 2026 in 209 ms. Over 5 checks since 14 September 2026 it answered 5.

How do I add Batchloom Evidence to Cursor?

Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://batchloom-studio-0913.xuikatwsicrdsidm.chatgpt.site/v1/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.

Does Batchloom Evidence need an API key?

It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.

Where this comes from

Publisher: site.chatgpt.xuikatwsicrdsidm.batchloom-studio-0913. Endpoint host: batchloom-studio-0913.xuikatwsicrdsidm.chatgpt.site. ARD identifier: urn:air:site.chatgpt.xuikatwsicrdsidm.batchloom-studio-0913:mcp:evidence. First indexed 14 September 2026. The tools are exactly what the server returned; nothing on this page is inferred from its name. Ranking in Neuronto search is never for sale.

Is this your server? Get a message the day it stops answering or its tools change: monitoring, 14 days free. Or claim the domain to manage how it is listed.