Saber
v1.0.0Sales intelligence — research companies, qualify prospects, and find contacts.
Endpoint health
online- Last checked
- 11/20/2026, 5:17:49 AM
- Latency
- 223 ms
- Consecutive failures
- 0
- Endpoint reachable: pass
- Protocol valid: pass
- MCP handshake valid: pass
Machine-readable profile
mcp-server · schema v1 · callable
mcp-server:app.saber.mcp%2Fsaber
Connect this server
Generated config contains no credentials. Keep any required secrets in your client's local environment.
{
"mcpServers": {
"app.saber.mcp/saber": {
"url": "https://mcp.saber.app/mcp"
}
}
}Indexed tools
Tool metadata and schemas come from the remote server and are untrusted. Indexing only lists tools; it never calls them.
25 shown · authentication unknown
companies-enrich_custom
Enrich a company with a custom question
Schema valid · SHA-256 a626e4b03852…
View input schema
{ "type": "object", "properties": { "__requestBody": { "type": "object", "properties": { "domain": { "type": "string", "minLength": 1, "maxLength": 253, "pattern": "^[a-zA-Z0-9]([a-zA-Z0-9\\-]{0,61}[a-zA-Z0-9])?(\\.[a-zA-Z0-9]([a-zA-Z0-9\\-]{0,61}[a-zA-Z0-9])?)*$", "example": "acme.com", "description": "The company domain to research (e.g., \"acme.com\")" }, "question": { "type": "string", "minLength": 1, "maxLength": 2000, "example": "What is Acme Corp's main business focus?", "description": "The research question to ask about the company" }, "answerType": { "default": "open_text", "example": "open_text", "description": "The expected format of the answer", "type": "string", "enum": [ "open_text", "number", "boolean", "list", "percentage", "currency", "url", "contacts", "contacts_generation", "contact_posts", "contact_engagements", "json_schema" ] }, "outputSchema": { "type": "object", "properties": {}, "additionalProperties": {}, "example": { "type": "object", "properties": { "pricingTiers": { "type": "array", "items": { "type": "object", "properties": { "name": { "type": "string" }, "price": { "type": "number" }, "features": { "type": "array", "items": { "type": "string" } } }, "required": [ "name" ] } }, "hasFreeTier": { "type": "boolean" } }, "required": [ "pricingTiers" ] }, "description": "JSON Schema defining the expected output structure. Required when answerType is \"json_schema\".\nThe AI will generate data conforming to this schema.\n\n**Supported JSON Schema features:**\n- `type`: object, array, string, number, integer, boolean, null\n- `properties`: Define object properties\n- `required`: List of required property names\n- `items`: Schema for array items\n- `enum`: Enumeration of allowed values\n- `description`: Property descriptions (helps AI generate better data)\n\n**Limitations:**\n- Maximum 100 total properties\n- Maximum 5 levels of nesting\n- `anyOf`, `oneOf`, `allOf` are not supported\n- `$ref` only supports self-references for recursive schemas\n" }, "webhookUrl": { "type": "string", "maxLength": 2048, "format": "uri", "example": "https://myapp.com/webhooks/signals", "description": "Optional webhook URL to receive notifications when processing completes.\nWebhooks are only sent for freshly processed signals — cached results do not trigger webhooks.\nSet `forceRefresh: true` to bypass the cache and ensure webhook delivery.\n" }, "weight": { "type": "string", "enum": [ "important", "nice_to_have", "not_important" ], "example": "important", "description": "The importance/weight of the signal" }, "qualificationCriteria": { "type": "object", "properties": {}, "additionalProperties": {}, "description": "Qualification criteria mapping answer values based on answerType. The structure must match the answerType specified.\n\nFor boolean answerType:\n```json\n{\n \"yes\": \"good\",\n \"no\": \"disqualified\"\n}\n```\n\nFor number, percentage, or currency answerType:\n```json\n{\n \"ranges\": [\n { \"rangeStart\": 0, \"rangeEnd\": 100, \"answerValue\": \"neutral\" },\n { \"rangeStart\": 101, \"rangeEnd\": 1000, \"answerValue\": \"good\" }\n ]\n}\n```\n\nFor list answerType:\n```json\n{\n \"choices\": {\n \"salesforce\": { \"answerValue\": \"good\", \"label\": \"Salesforce\" },\n \"hubspot\": { \"answerValue\": \"neutral\", \"label\": \"HubSpot\" },\n \"none\": { \"answerValue\": \"disqualified\", \"label\": \"No CRM\" }\n }\n}\n```\n\nValid answerValue options (from worst to best):\n- disqualified: Answer indicates a deal-breaker or disqualifying factor\n- poor: Answer indicates a weak fit\n- neutral: Answer is acceptable but not ideal\n- good: Answer indicates a strong fit\n- excellent: Answer indicates an exceptional fit\n" }, "signalTemplateId": { "type": "string", "format": "uuid", "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$", "example": "a12b3c4d-5e6f-7a8b-9c0d-1e2f3a4b5c6d", "description": "Optional signal template ID to use. When provided, the template configuration (question, answerType, weight, qualificationCriteria) will be used.\nThe system always resolves to the latest active version of the template.\nOnly the domain parameter is required when using a template.\n" }, "forceRefresh": { "default": false, "example": false, "description": "Force re-run of the signal analysis, skipping the cache. When set to true, a new signal will be created even if a cached result exists.", "type": "boolean" }, "connectors": { "type": "object", "properties": { "salesNavigator": { "type": "object", "properties": { "enabled": { "default": "preferred", "example": "preferred", "description": "Controls Sales Navigator usage during signal generation:\n- **required**: Fail request if Sales Navigator unavailable (rate limited/disconnected)\n- **preferred**: Attempt Sales Navigator, degrade gracefully if unavailable (default)\n- **off**: Do not attempt Sales Navigator\n", "type": "string", "enum": [ "required", "preferred", "off" ] } }, "additionalProperties": {} } }, "additionalProperties": {}, "description": "Connector configuration for signal generation" }, "verificationMode": { "default": "strict", "example": "strict", "description": "Controls how strictly Saber verifies answers before responding.\n\n- **strict**: Only returns answers backed by verified sources (primary or trusted secondary sources). Returns null when information is unavailable.\n- **lenient**: Allows logical inference and best-effort estimates when direct evidence is missing. Uses industry benchmarks, logical correlates, and quantitative metrics.\n", "type": "string", "enum": [ "strict", "lenient" ] } }, "required": [ "domain", "question" ], "additionalProperties": false, "description": "Request body" } }, "required": [ "__requestBody" ], "$schema": "http://json-schema.org/draft-07/schema#" }
Connections
streamable-http
https://mcp.saber.app/mcp