AI & Machine Learning

llmexpert.io

Manages channel knowledge bases by adding and listing sources and running retrieval-augmented queries that return cited answers.

x402 supported1 endpoint13 known toolsFirst detected October 19, 2026Last detected October 19, 2026

ENDPOINT 1

https://llmexpert.io/mcp

No auth detected

MCP server metadata

Name: llmexpert-mcp-shim
Version: 0.2.0

Capabilities

tools.listChanged

Server instructions

Thin, stateless bridge to the LLMExpert.io /v1 API. Each tool maps 1:1 onto a /v1 endpoint. Present your /v1 API key as `Authorization: Bearer <key>`; it is forwarded unchanged so the same scopes, rate limits, and spend caps apply. A `ct_` collection token (returned once by `transcribe` or `create_collection`) is accepted the same way for `get_status` and `get_transcript`. `transcribe`, `add_sources` and `query_collection` are charged: call `quote` first for the exact price, then poll `get_status` every 10–30 s until the job is completed, partial or failed. Without an API key, `transcribe` and `query_collection` are payable in USDC via x402: retry the payment-required result with `_meta['x402/payment']`; never pay again on a 409 or 502.

Known tools 13

query_channel

Run a retrieval-augmented query against a channel's indexed knowledge base and return a generated answer with citations.

Inferred read-only

list_channels

List the channels the calling key is scoped to.

Inferred read-only

list_sources

List the sources (video/document/website) in a channel, optionally filtered by type or status.

Inferred read-only

get_source

Fetch a single source and its processing status (type-specific provenance included).

Inferred read-only

add_source

Add a source to a channel and begin background ingestion.

Inferred read-only

get_usage

Get usage, quota, and spend for the calling key (queries, tokens, cost, budget remaining).

Inferred read-only

quote

Free.

Inferred read-only

transcribe

Charged.

Inferred read-only

create_collection

Free.

Inferred read-only

add_sources

Charged like `transcribe`.

Inferred read-only

get_status

Free.

Inferred read-only

get_transcript

Free.

Inferred read-only

query_collection

Charged: $0.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

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

Codex

~/.codex/config.toml

[mcp_servers.llmexpert-mcp-shim]
url = "https://llmexpert.io/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "llmexpert-mcp-shim": {
      "type": "http",
      "url": "https://llmexpert.io/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: llmexpert-mcp-shim
Remote MCP URL: https://llmexpert.io/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": {
    "llmexpert-mcp-shim": {
      "url": "https://llmexpert.io/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "llmexpert-mcp-shim": {
      "type": "http",
      "url": "https://llmexpert.io/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "llmexpert-mcp-shim",
  "transport": "streamable-http",
  "url": "https://llmexpert.io/mcp"
}

MCP Inspector

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

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.