Opensearch MCP tools

Use this reference to find a tool and its inputs. Connect an MCP client before calling tools. Tool visibility depends on discovery and permissions.

For actions that send messages, spend credits, delete data, or start execution, review the intended records and confirm the action before proceeding. Obtain IDs from a prior result; do not invent them. A registered tool does not guarantee that its supporting service is available in every organization.

g8_opensearch_aggregate

Generic GROUP BY over a whitelisted mashup index — the TAM matrix-walk primitive. Counts company/contact distributions across 1-3 dimensions in one call (e.g. NAICS x state x employee band). Aggregations on contact/company mashup indices automatically apply the organization’s deliverability protection policy. Args: index: One of “mashup_contacts”, “mashup_companies”, “hem2contact”, “ip2company”. group_by: 1-3 RAW UPPERCASE keyword fields to group on, e.g. [“COMPANY_NAICS”, “COMPANY_STATE”]. Capped at 3 dimensions. filters: Pre-aggregation equality filters (same shape as search). agg: Metrics per group. Each item is {“function”: …, “field”: …, “alias”: …}. function in count/uniqExact/sum/avg/min/max. count needs no field; the rest require one. Defaults to a single count. For unique companies: {“function”: “uniqExact”, “field”: “COMPANY_ID”, “alias”: “companies”}. having: Post-aggregation group filter keyed by alias, e.g. {“count”: {“gte”: 50}}. Operators: eq, gte, lte, gt, lt. sort: Sort groups by an alias, e.g. [{“count”: “desc”}]. limit: Max groups returned (default 100, server-capped at 1000).

Inputs

Input	Required	Type	Description
index	Yes	string	See the schema below for constraints and defaults.
group_by	Yes	array	See the schema below for constraints and defaults.
filters	No	object / null	See the schema below for constraints and defaults.
agg	No	array / null	See the schema below for constraints and defaults.
having	No	object / null	See the schema below for constraints and defaults.
sort	No	array / null	See the schema below for constraints and defaults.
limit	No	integer	See the schema below for constraints and defaults.

Complete input schema

{
  "properties": {
    "index": {
      "title": "Index",
      "type": "string"
    },
    "group_by": {
      "items": {
        "type": "string"
      },
      "title": "Group By",
      "type": "array"
    },
    "filters": {
      "anyOf": [
        {
          "additionalProperties": true,
          "type": "object"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Filters"
    },
    "agg": {
      "anyOf": [
        {
          "items": {
            "additionalProperties": true,
            "type": "object"
          },
          "type": "array"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Agg"
    },
    "having": {
      "anyOf": [
        {
          "additionalProperties": {
            "additionalProperties": {
              "type": "number"
            },
            "type": "object"
          },
          "type": "object"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Having"
    },
    "sort": {
      "anyOf": [
        {
          "items": {
            "additionalProperties": {
              "type": "string"
            },
            "type": "object"
          },
          "type": "array"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Sort"
    },
    "limit": {
      "default": 100,
      "title": "Limit",
      "type": "integer"
    }
  },
  "required": [
    "index",
    "group_by"
  ],
  "title": "g8_opensearch_aggregateArguments",
  "type": "object"
}

g8_opensearch_count

Exact match count for a whitelisted mashup index (TAM cell sizing). Same index + filters shape as g8_opensearch_search, but returns just {index, count} via the native OpenSearch _count API — NOT capped at the 10000 ceiling that search’s total saturates at. Counts on contact/company mashup indices automatically apply the organization’s deliverability protection policy. Note: mashup_companies and mashup_contacts are the SAME contact-grained index, so a count on mashup_companies counts contact rows, not unique companies. For a unique-company total use g8_opensearch_aggregate with uniqExact on COMPANY_ID. Args: index: One of “mashup_contacts”, “mashup_companies”, “hem2contact”, “ip2company”. filters: Field equality filters, AND-joined. RAW UPPERCASE field names, e.g. {“COMPANY_NAICS”: [“3311”, “3311.00000”], “COMPANY_COUNTRY”: [“US”, “United States”]}.

Inputs

Input	Required	Type	Description
index	Yes	string	See the schema below for constraints and defaults.
filters	No	object / null	See the schema below for constraints and defaults.

Complete input schema

{
  "properties": {
    "index": {
      "title": "Index",
      "type": "string"
    },
    "filters": {
      "anyOf": [
        {
          "additionalProperties": true,
          "type": "object"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Filters"
    }
  },
  "required": [
    "index"
  ],
  "title": "g8_opensearch_countArguments",
  "type": "object"
}

g8_opensearch_resolve_ids

Bulk HEM -> CONTACT_ID or IP -> COMPANY_ID resolution. Take a batch of opaque IDs and get back the canonical graph8 CONTACT_ID / COMPANY_ID. Args: kind: “hem_to_contact” or “ip_to_company”. ids: Up to 500 input IDs. The response includes EVERY input as a key (null for misses) so you can iterate without re-querying.

Inputs

Input	Required	Type	Description
kind	Yes	string	See the schema below for constraints and defaults.
ids	Yes	array	See the schema below for constraints and defaults.

Complete input schema

{
  "properties": {
    "kind": {
      "title": "Kind",
      "type": "string"
    },
    "ids": {
      "items": {
        "type": "string"
      },
      "title": "Ids",
      "type": "array"
    }
  },
  "required": [
    "kind",
    "ids"
  ],
  "title": "g8_opensearch_resolve_idsArguments",
  "type": "object"
}

g8_opensearch_search

Structured search against the graph8 OpenSearch mashup indices. Use when the higher-level CRM tools (g8_find_contacts, g8_lookup_person) don’t surface the filter you need. For ID-only resolution prefer g8_opensearch_resolve_ids (single round trip). For a count with no rows prefer g8_opensearch_count; for GROUP BY use g8_opensearch_aggregate. Contact/company mashup results automatically apply the organization’s deliverability protection policy. Args: index: Logical index name. One of: “mashup_contacts” (person-level enrichment), “mashup_companies” (company-level enrichment), “hem2contact” (HEM -> CONTACT_ID), “ip2company” (IP -> COMPANY_ID). filters: Field equality filters, AND-joined. List values become a terms clause. E.g. {“COMPANY_DOMAIN”: “acme.com”}, {“COMPANY_INDUSTRY”: [“SaaS”, “Fintech”]}. Use RAW UPPERCASE field names (e.g. COMPANY_INDUSTRY, not “industry”). fields: Optional _source columns to return. Omit for full document. limit: Max hits (default 50, server-capped at 200). sort: Optional sort spec, e.g. [{“COMPANY_REVENUE”: “desc”}]. Required if paginating via cursor. cursor: search_after token from a prior call (the sort field of the last hit). Pass back to fetch the next page. track_total_hits: Optional exact-count ceiling for total (e.g. 100000). Omit for the default 10000-saturating behaviour.

Inputs

Input	Required	Type	Description
index	Yes	string	See the schema below for constraints and defaults.
filters	No	object / null	See the schema below for constraints and defaults.
fields	No	array / null	See the schema below for constraints and defaults.
limit	No	integer	See the schema below for constraints and defaults.
sort	No	array / null	See the schema below for constraints and defaults.
cursor	No	array / null	See the schema below for constraints and defaults.
track_total_hits	No	integer / null	See the schema below for constraints and defaults.

Complete input schema

{
  "properties": {
    "index": {
      "title": "Index",
      "type": "string"
    },
    "filters": {
      "anyOf": [
        {
          "additionalProperties": true,
          "type": "object"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Filters"
    },
    "fields": {
      "anyOf": [
        {
          "items": {
            "type": "string"
          },
          "type": "array"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Fields"
    },
    "limit": {
      "default": 50,
      "title": "Limit",
      "type": "integer"
    },
    "sort": {
      "anyOf": [
        {
          "items": {
            "additionalProperties": {
              "type": "string"
            },
            "type": "object"
          },
          "type": "array"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Sort"
    },
    "cursor": {
      "anyOf": [
        {
          "items": {},
          "type": "array"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Cursor"
    },
    "track_total_hits": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Track Total Hits"
    }
  },
  "required": [
    "index"
  ],
  "title": "g8_opensearch_searchArguments",
  "type": "object"
}