The server lets AI clients query Biel.ai’s specialized AI for code, SDK, and documentation answers; the supplied schema exposes only biel_ai.
Ask natural-language questions about code, SDKs, or technical documentation.
Continue a conversation by passing a chat_uuid.
Tag conversation sources with optional metadata.
Support private or domain-restricted projects via api_key and domain.
Per the README, the broader MCP server also supports hybrid search and full document retrieval (biel_search, biel_get_document), though those tools are not present in this schema.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Biel AI what are the authentication requirements for the billing API?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Biel.ai turns technical documentation into answers for users and context for AI agents, with links back to the sources. This MCP server connects Claude Code, Codex, Cursor, and other compatible clients to documentation indexed in a Biel.ai project.
The usual workflow is to search for relevant content, retrieve indexed documents when more context is needed, and answer in the calling AI assistant. Biel.ai can also generate an answer when you explicitly request one. Source grounding does not eliminate model error; check the retrieved content and references.
Requires a Biel.ai account, indexed sources, and hosted MCP enabled on a plan that includes it. Create an account and follow the MCP setup guide.
Open your project in Biel.ai, go to Settings > MCP, enable the MCP server, and save. Copy the complete endpoint supplied for your project.
Use the canonical documentation for client-specific steps:
For Cursor and VS Code / Copilot, use the widget's Connect menu or the manual setup guide.
The example configuration uses mcp-remote as a bridge for clients without native Streamable HTTP support. Clients with native HTTP support should connect directly using their own configuration format.
Confirm the client discovers biel_search, biel_get_document, and biel_ai. Ask a question your indexed documentation covers:
Use biel_search to find our API authentication instructions. Read relevant
results with biel_get_document and explain the required headers with source links.Check the retrieved text and citations against the documentation. MCP serves indexed content; refresh sources in Biel.ai after documentation changes and search again for current document IDs.
Related MCP server: local_lense
The server exposes three tools:
biel_ai: ask Biel.ai to generate an answer, with conversational context. Existing calls using message continue to generate answers.
biel_search: hybrid keyword and semantic search over indexed web pages, uploaded files, repositories and OpenAPI sources, without answer generation.
biel_get_document: read the complete indexed text of a document returned by search.
Call biel_search with a natural-language question or search terms:
{"query": "How do I authenticate with the SDK?", "limit": 5}Search requests the API's search_type=hybrid&source_types=all. The REST API defaults to search_type=keyword, independently of the selected sources. Results include chunk text, source type, a document_id, and any page/sheet reference; non-URL documents are cited by title and location. The limit argument controls how many chunks are returned (default 5, maximum 20).
Use biel_get_document with a search result's document_id to read the complete indexed document without visiting its source site:
{"document_id": "DOCUMENT_ID_FROM_SEARCH", "limit": 20}Public projects do not need an API key. Private projects require an api_key query parameter with search permission for retrieval and chats_create for generated answers.
A domain query parameter is needed when allowed domains are configured. See connection parameters before connecting a private or domain-restricted project. Treat a URL containing a key as a credential and keep it out of shared configuration.
For advanced users who prefer to run their own MCP server instance:
# Clone and run locally
git clone https://github.com/TechDocsStudio/biel-mcp
cd biel-mcp
pip install .
biel-mcpApplications that host their own ASGI stack can install the server directly from a tagged revision and import its FastAPI application:
pip install "biel-mcp @ git+https://github.com/TechDocsStudio/biel-mcp.git@VERSION"from biel_mcp.server import app# Docker Compose (recommended)
docker-compose up -d --build
# Or Docker directly
docker build -t biel-mcp .
docker run -d -p 7832:7832 biel-mcpIssues: GitHub Issues
Contact: support@biel.ai
Custom Demo: Book a demo
Query Biel.ai's specialized AI about code, SDKs and documentation
| Name | Required | Description | Default |
|---|---|---|---|
| domain | No | Domain URL. Required only if 'Allowed domains' is enabled in project settings. | |
| api_key | No | API key for authentication (optional) | |
| message | Yes | Your question about code, SDK or documentation | |
| metadata | No | Metadata to tag the conversation source (optional) | |
| chat_uuid | No | Chat UUID to continue conversation (optional) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of disclosing behavioral traits. It only says 'Query,' which implies a read-like operation, but does not disclose that this may send data to an external AI service, require authentication (though params suggest an API key), or have any side effects. Important behavioral context such as network calls, data privacy, or response handling is omitted.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, focused sentence that front-loads the action and purpose without any filler. It is concise and well-structured, though it could potentially add a hint about response format or usage context without becoming verbose. Still, it earns its place and is not over-specified.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
While the input schema comprehensively documents all parameters, the description lacks guidance on what the AI returns (no output schema) and does not explain the broader context of how the tool should be invoked (e.g., optional domain, API key, chat continuation). For a query tool with 5 parameters, this is adequately functional but not rich enough to fully guide an agent without further clues.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema description coverage is 100%, with all five parameters individually described in the input schema. The tool description itself adds no parameter-specific semantics beyond what the schema already provides. As a result, a baseline score of 3 is appropriate; the schema does the heavy lifting, and the description does not enhance understanding of parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's function: querying Biel.ai's specialized AI about code, SDKs, and documentation. It uses a specific verb ('Query') and resource ('Biel.ai's specialized AI'), making the purpose distinct even without sibling tools to differentiate from. However, the term 'specialized AI' is somewhat generic, which prevents a perfect score.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives, and no exclusion criteria. Since there are no sibling tools or context signals, the agent is left without explicit usage conditions or scenarios where this tool should or shouldn't be used. This is a clear gap in usage guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v2.0.0biel_aiScored across 1 tool
With only one tool, there is no ambiguity between tools. The tool's description clearly states its purpose, making selection straightforward.
The single tool name 'biel_ai' is clear and consistent with the server name. No pattern inconsistencies are possible with only one tool.
A single tool is on the low end, feeling thin for a server that might expect to offer more capabilities. It is not trivial, but the number is borderline and may be insufficient for broader use cases.
The tool covers the basic need of querying the specialized AI. However, there may be missing operations such as managing sessions or retrieving context, which could be expected in a full-featured AI interface.
Connect Claude, Cursor, or ChatGPT to your business data. Ask questions, get answers.
Cloud or self-hosted knowledge for AI agents: hybrid search, reranking, GraphRAG, scoped MCP tools.
Self-hosted AI workspace: semantic RAG document search, long-term memory, and AI chat via MCP.
Connect your team's living knowledge base — docs, data, issues, CRM — to Claude and ChatGPT.
