Tutorial: Resolver - Gnist Context

Platform

Data source: Internal registry

Overview

Resolver wraps Internal registry, handling authentication, pagination, and rate limits for you. This tutorial covers all 4 tools with working code examples you can copy and run.

Prerequisites

Sign up at https://context.gnist.ai/signup for a free API key (100 calls/day).
Choose your integration method: MCP protocol or REST API.

Connect via MCP

Add to your MCP client config (Claude Desktop, Cursor, etc.):

MCP Config

{
  "mcpServers": {
    "gnist-resolver": {
      "url": "https://context.gnist.ai/mcp/resolver/",
      "headers": {
        "Gnist-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Tools (4)

`resolve_entity`

Resolve an entity name to canonical identifiers across all relevant Gnist Context servers. Given a name and type, queries multiple upstream servers in parallel and returns a unified identity card with native identifiers per source. Results are cached for 24 hours. Args: name: Entity name to resolve. Examples: "Equinor", "Albert Einstein", "Norway", "machine learning" entity_type: Type of entity. One of: company, person, country, research_topic. hints: Optional dict of hints to narrow resolution. For company: {"country": "NO"} to include Norwegian registry (Brreg). For country: {"code": "NO"} to query economic databases by code. Returns: Identity card with: - canonical_name: Best-match canonical name - entity_type: The resolved type - identifiers: Dict keyed by source (brreg, gleif, wikidata, etc.), each containing the source's native identifiers - sources_ok / sources_failed: Resolution success counts - cached: Whether result came from cache

Parameter	Type	Required	Description
`name`	string	required	Entity name to resolve.
`entity_type`	string	required
`hints`	any	optional

curl -X POST "https://context.gnist.ai/mcp/resolver/" \
  -H "Content-Type: application/json" \
  -H "Gnist-API-Key: YOUR_API_KEY" \
  -d '{"jsonrpc": "2.0", "method": "tools/call", "id": 1, "params": {"name": "resolve_entity", "arguments": {"name": "example", "entity_type": "example"}}}'

import httpx

resp = httpx.post(
    "https://context.gnist.ai/mcp/resolver/",
    headers={"Gnist-API-Key": "YOUR_API_KEY"},
    json={'id': 1,
 'jsonrpc': '2.0',
 'method': 'tools/call',
 'params': {'arguments': {'entity_type': 'example', 'name': 'example'},
            'name': 'resolve_entity'}},
)
print(resp.json())

`list_entity_types`

List all entity types available for resolution. Returns the type name, description, and which upstream resolvers are configured for each type. Returns: Dict with count and entity_types list.

curl -X POST "https://context.gnist.ai/mcp/resolver/" \
  -H "Content-Type: application/json" \
  -H "Gnist-API-Key: YOUR_API_KEY" \
  -d '{"jsonrpc": "2.0", "method": "tools/call", "id": 1, "params": {"name": "list_entity_types", "arguments": {}}}'

import httpx

resp = httpx.post(
    "https://context.gnist.ai/mcp/resolver/",
    headers={"Gnist-API-Key": "YOUR_API_KEY"},
    json={'id': 1,
 'jsonrpc': '2.0',
 'method': 'tools/call',
 'params': {'arguments': {}, 'name': 'list_entity_types'}},
)
print(resp.json())

`resolver_cache_stats`

Return statistics about the entity resolution cache. Returns: Dict with entries, valid, expired, max_size, and ttl_seconds.

curl -X POST "https://context.gnist.ai/mcp/resolver/" \
  -H "Content-Type: application/json" \
  -H "Gnist-API-Key: YOUR_API_KEY" \
  -d '{"jsonrpc": "2.0", "method": "tools/call", "id": 1, "params": {"name": "resolver_cache_stats", "arguments": {}}}'

import httpx

resp = httpx.post(
    "https://context.gnist.ai/mcp/resolver/",
    headers={"Gnist-API-Key": "YOUR_API_KEY"},
    json={'id': 1,
 'jsonrpc': '2.0',
 'method': 'tools/call',
 'params': {'arguments': {}, 'name': 'resolver_cache_stats'}},
)
print(resp.json())

`report_feedback`

Report a bug, feature request, or general feedback for this data source. Use this when something doesn't work as expected, when you'd like a new feature, or when you have suggestions for improvement. Args: feedback: Describe the issue or suggestion. feedback_type: One of 'bug', 'feature_request', or 'general'.

Parameter	Type	Required	Description
`feedback`	string	required
`feedback_type`	string	optional	(default: `general`)

curl -X POST "https://context.gnist.ai/mcp/resolver/" \
  -H "Content-Type: application/json" \
  -H "Gnist-API-Key: YOUR_API_KEY" \
  -d '{"jsonrpc": "2.0", "method": "tools/call", "id": 1, "params": {"name": "report_feedback", "arguments": {"feedback": "example"}}}'

import httpx

resp = httpx.post(
    "https://context.gnist.ai/mcp/resolver/",
    headers={"Gnist-API-Key": "YOUR_API_KEY"},
    json={'id': 1,
 'jsonrpc': '2.0',
 'method': 'tools/call',
 'params': {'arguments': {'feedback': 'example'}, 'name': 'report_feedback'}},
)
print(resp.json())

FAQ

What data does Resolver provide?

Cross-server entity resolution — resolve names to canonical identifiers across all data servers. It exposes 4 tools: resolve_entity, list_entity_types, resolver_cache_stats, report_feedback.

What do I need to get started?

A Gnist API key (free tier: 100 calls/day). Sign up at https://context.gnist.ai/signup.

What format does the Resolver API return?

JSON, via either MCP protocol (JSON-RPC 2.0) or REST API.