INDIVIDUAL MCP TOOL

validate_run_bundle

Run the runtime's RunBundle schema + structural invariants against arbitrary JSON.

llmworkbench.ionone authenticationAvailability not checked

LIVE ENDPOINT

https://www.llmworkbench.io/api/mcp

No auth detected

Connect to this endpoint to inspect the live schema for validate_run_bundle and invoke it with your own arguments.

{}

Inferred read-only · medium confidence · heuristic, not a guarantee.

No write-capable action terms were found; this is not proof that invocation has no side effects.

CONNECT WITH APPROVAL

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.llm-workbench]
url = "https://www.llmworkbench.io/api/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "llm-workbench": {
      "type": "http",
      "url": "https://www.llmworkbench.io/api/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: llm-workbench
Remote MCP URL: https://www.llmworkbench.io/api/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "llm-workbench": {
      "url": "https://www.llmworkbench.io/api/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "llm-workbench": {
      "type": "http",
      "url": "https://www.llmworkbench.io/api/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "llm-workbench",
  "transport": "streamable-http",
  "url": "https://www.llmworkbench.io/api/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

list_runs — Return SavedRunMeta[] for the configured RunRepository.
get_run — Return the serialized RunStoreState for a runId.
verify_run_integrity — Verify a RunBundle's `integrity.sha256` against its canonical JSON.
start_run — Start a new run from a workflow id.
resolve_gate — Resolve a human gate for a step.
write_artifact — Write a typed artifact to a run.
export_bundle — Return a tamper-evident RunBundle JSON for the run (full profile, with engine snapshot).