Descovo — B2B contact data
B2B contact data for AI agents: search 700M+ people, reveal work emails. Pay per record.
我该使用它吗
质量与安全性
基于对工具定义和协议合规性的自动分析。
上下文开销
这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高，可用于其他任务的注意力就越少。
安装
一键安装
将以下内容添加到你的 `claude_desktop_config.json` 文件中：
{
"mcpServers": {
"descovo": {
"url": "https://mcp.descovo.com/mcp"
}
}
}远程端点
https://mcp.descovo.com/mcpstreamable-http它能做什么
工具清单
工具（5）
🟢search_endpoints(query, constraints, preferredTags, excludedTags, tagPack, ...)
Canonical API selection tool for endpoint discovery and ranking. Use this first to get the top recommended operations for a user intent. Supports optional constraints plus tag-scoped selection via preferredTags, excludedTags, or a curated tagPack key.
输入模式
{
"type": "object",
"properties": {
"query": {
"type": "string"
},
"constraints": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null
},
"preferredTags": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null
},
"excludedTags": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null
},
"tagPack": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null
},
"limit": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"default": null
}
},
"required": [
"query"
],
"additionalProperties": false
}输出模式
{
"type": "object",
"additionalProperties": true
}🟢list_tag_packs
List curated tag packs for large tool catalogs. Use this to narrow exploration (for example social-media or enrichment).
输入模式
{
"type": "object",
"properties": {},
"additionalProperties": false
}输出模式
{
"type": "object",
"additionalProperties": true
}🟢list_all_endpoints(tags, search, tagPack, limit)
List available Descovo API endpoints with optional tag/search filtering.
输入模式
{
"type": "object",
"properties": {
"tags": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null
},
"search": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null
},
"tagPack": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null
},
"limit": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"default": null
}
},
"additionalProperties": false
}输出模式
{
"type": "object",
"additionalProperties": true
}🟢get_endpoint_details_full(operationId)
Get COMPLETE schema and details for a specific API operation. Use this BEFORE calling an API to understand exactly what parameters are needed. Args: operationId: The operation ID (e.g., "syncContactEnrichment") Returns: Complete schema including all required/optional fields, request body schema, response schema, and example usage.
输入模式
{
"type": "object",
"properties": {
"operationId": {
"type": "string"
}
},
"required": [
"operationId"
],
"additionalProperties": false
}输出模式
{
"type": "object",
"additionalProperties": true
}🟢call_operation(operationId, params)
Execute any Descovo API operation by operationId. IMPORTANT: - apiKey is NOT required in the body if the MCP client sends an x-api-key header (most configs do). The backend auto-injects it. - Prefer search_endpoints() first when operation choice is ambiguous. - Use get_endpoint_details_full(operationId='...') first for complex/nested parameter shapes. Args: operationId: The operation ID to call params: Parameters dict: {"body": {...}, "path": {...}, "query": {...}} Returns: API response data or error details.
输入模式
{
"type": "object",
"properties": {
"operationId": {
"type": "string"
},
"params": {
"default": null,
"title": "Params"
}
},
"required": [
"operationId"
],
"additionalProperties": false
}输出模式
{
"type": "object",
"additionalProperties": true
}社区
证据