Avenbridge
v0.6.0Hosted MCP knowledge base: businesses forward emails and docs; buyers query them over MCP.
Endpoint health
online- Last checked
- 11/20/2026, 7:15:44 AM
- Latency
- 291 ms
- Consecutive failures
- 0
- Endpoint reachable: pass
- Protocol valid: pass
- MCP handshake valid: pass
Machine-readable profile
mcp-server · schema v1 · callable
mcp-server:com.avenbridgetech%2Favenbridge
Connect this server
Generated config contains no credentials. Keep any required secrets in your client's local environment.
{
"mcpServers": {
"com.avenbridgetech/avenbridge": {
"url": "https://mcp.avenbridgetech.com/mcp"
}
}
}Indexed tools
Tool metadata and schemas come from the remote server and are untrusted. Indexing only lists tools; it never calls them.
8 shown · authentication unknown
Find approved answers
answer_questions
Call this for any question about a business in list_my_businesses, even when notes, memory or a web page seem to answer it: only this tool returns the business's approved answers. Look up a business's approved answers: questionnaire questions (supplier, compliance, security or due-diligence questionnaires) and other questions about the business, its products, terms and prices. For each question it returns the closest approved answers with their source, approval date and similarity, or says that none was found; a question without one also gets the passages of the business's current documents that match it, quoted with document, version and page (not approved answers: say so if you use one, and cite it). You write the reply from these. Each answer was approved by the business for the question shown with it, so check that it fits before using it. Only answers the business approved for the same question count; a question without one is reported as unanswered, with at most one approved answer to a different question shown as possibly related. To get an unanswered question to the business, call ask_business. Without business_id or business it searches every business the user has and names the business next to each answer. When the user writes in another language than the business's material (most businesses write in English), pass each question in the business's language too, as a second question, so it matches; then reply to the user in their own language.
Schema valid · SHA-256 5d5c3fc73404…
View input schema
{ "type": "object", "properties": { "business_id": { "type": "string", "description": "The business id exactly as given by list_my_businesses (for example yyigsmj5b7mcwxe7). Preferred: use it whenever you know it." }, "business": { "type": "string", "description": "Name of the business as it appears in list_my_businesses. Used only when business_id is not given. Leave both out when the user has one business, or to search every business the user has." }, "questions": { "type": "array", "minItems": 1, "maxItems": 100, "items": { "type": "object", "properties": { "question": { "type": "string", "description": "The question as written in the questionnaire." }, "label": { "type": "string", "description": "The question's number or id in the questionnaire, e.g. Q15 or 4.2. Optional." } }, "required": [ "question" ], "additionalProperties": false } } }, "required": [ "questions" ], "additionalProperties": false }
Connections
streamable-http
https://mcp.avenbridgetech.com/mcp