Explorium AgentSource vs Fuse MCP

Explorium AgentSource

AgentSource v2 has a public OpenAPI 3.1 file, Markdown docs, a 200 queries a minute limit with Retry-After, public credit prices and a 100-credit trial. No status page or published SLA was found, each company shares one API key with no scopes, and the vendor's two published price tables disagree.

Fuse MCP

The server documents 290 tools with read-only and destructive annotations, OAuth with PKCE and dynamic client registration, and published limits of 60 requests a minute. The single mcp:tools scope grants everything the user can do, sends happen at once with no undo, and no status page, changelog or security contact was found.

Explorium AgentSource

1. Send the key in the api_key header to https://api.explorium.ai and use /v2 paths. v1 is deprecated
2. Point MCP clients at https://mcp-v2.explorium.ai/mcp. The site's agent files still name the v1 server at mcp.explorium.ai
3. Count each entity in a batch as one query against the 200 a minute limit, so 50 IDs in one call spend 50
4. Call the statistics endpoint first to size an audience for free. Fetch costs 1 credit a result, or 2 with the Bombora intent filter
5. Call /v2/autocomplete before filtering on category, tech stack or job title, and never mix two category types in one request

Fuse MCP

1. Keep the client's approval prompt on for every tool that is not read-only. Sends, CRM pushes and Slack posts run at once with no undo
2. Launch a campaign only on an explicit request. Creating one makes a draft, and update_campaign_status_tool starts real outreach
3. Call get_credits_balance and get_credit_prices first. Every call needs at least 100 credits, and searches cost 2 credits a result
4. Resolve filter values with lookup_filter_values or get_company_search_enums before search_people or search_companies
5. Start long work with deep_research_start, then poll deep_research_status. A tool call has 60 seconds, and runs take 5 to 20 minutes