biel_ai
Query Biel.ai's specialized AI about code, SDKs and documentation
LABSCO SUMMARY
chat_uuid is what turns this from a lookup into a conversation.
Passing it back keeps a thread alive, so a follow-up question does not have to restate what the first one established. The domain parameter scopes the answer to the right documentation site, and metadata is where anything the answer should be conditioned on belongs. With a single tool, everything about the shape of the answer comes down to how the message is written — there are no filters or modes to reach for.
What it is
A single-tool client for Biel.ai: a query against a documentation-trained AI scoped to one project.
What you get
- biel_ai queries Biel.ai's specialised AI about code, SDKs and documentation, taking the message plus the project's documentation domain, an optional api_key, a chat_uuid to continue an existing conversation, and metadata that travels with the query.
Requirements
A Biel.ai project — its slug and documentation domain decide which corpus a query runs against, and an api_key can travel with the call.
Setup effort
Get your endpoint, then paste it — add your endpoint to your client
USE CASES
01
Asking a documentation question and following it up in the same thread
The domain scopes the answer to the right documentation site, and passing the chat id back keeps the follow-up from having to restate the context.
1 tool
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
BEFORE YOU INSTALL
What to know first
Tools you get
1 tool when we connected.
Requires
npx on PATH
CONTEXT COST
Light Standing cost
Rated by the size of the one tool definition that rides along on every turn
INSTALLATION
Connect your client
This one is configured rather than run — your client needs the configuration block, not a command.
Server setup
JSON
{
"mcpServers": {
"mcp-remote": {
"command": "npx",
"args": [
"mcp-remote",
"https://mcp.biel.ai/sse?project_slug=<YOUR_PROJECT_SLUG>&domain=<YOUR_DOMAIN>"
]
}
}
}
