Skip to content

Exepal MCP server

Which MCP servers are Exepal's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-31

← Back to Exepal

Whose server it is
  • Registry namecom.exepal/exepalverified in the MCP registry

The registry name sits under exepal.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-31
  • Stateanswerschecked 2026-10-31
  • Tools10
  • Server calls itselfexepal
  • Server version1.0.0
  • Protocol version2025-06-18

On 2026-10-31 the server answered initialize and tools/list without a sign-in. First answer in 226 ms.

Should an agent connect itNot proven either way yet
  • Its tools do every use case we checked: check whether chatgpt and claude recommend a brand; vet a creator's fake follower risk before a deal; enrich a list of domains into company profiles for outreach.
  • Checked on 3 of the 7 days it takes to judge reliability.

Once connected

  • For "check whether chatgpt and claude recommend a brand", the likely first call is ai_visibility.
  • For "vet a creator's fake follower risk before a deal", the likely first call is creator_vetting.
  • For "enrich a list of domains into company profiles for outreach", the likely first call is company_enrich_batch.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 3, the first on 2026-10-31
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 3 so far
  • What an agent can do with it3 of 3 use cases
  • Answeredmeasuring3 of the 7 daily checks it takes to print a share
  • Median first answer184 ms
  • Space in an agent's context≈ 4,312 tokensthe definitions of all its tools (26), which an agent carries on every turn
  • Tool definitionsA · 99 of 100
  • Typed results0 of 26 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 2 of 26

What an agent can do with it

  • can do · check whether chatgpt and claude recommend a brand
  • can do · vet a creator's fake follower risk before a deal
  • can do · enrich a list of domains into company profiles for outreach

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

None of the five warning signs in these definitions.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers10 tools · read 2026-10-31
  • ai_visibility_quick

    AI brand visibility, quick check (5 prompts, 1 engine). Price: $0.50 USDC per call on Base, paid with x402; not charged if the call fails.

  • ai_visibility

    AI brand visibility report (20 prompts, all engines). Price: $3.00 USDC per call on Base, paid with x402; not charged if the call fails.

  • ai_visibility_deep

    AI brand visibility deep report (50 prompts, all engines). Price: $7.00 USDC per call on Base, paid with x402; not charged if the call fails.

  • creator_vetting

    Creator vetting score for one profile (fetches the profile if stats not supplied). Price: $0.20 USDC per call on Base, paid with x402; not charged if the call fails.

  • company_enrich

    Company enrichment for one domain. Price: $0.10 USDC per call on Base, paid with x402; not charged if the call fails.

  • company_enrich_batch

    Company enrichment for up to 10 domains. Price: $0.80 USDC per call on Base, paid with x402; not charged if the call fails.

  • ad_creative_score

    Score one ad creative. Price: $0.25 USDC per call on Base, paid with x402; not charged if the call fails.

  • ad_creative_score_batch

    Score up to 10 ad creatives. Price: $2.00 USDC per call on Base, paid with x402; not charged if the call fails.

  • serp_ai_monitor

    SERP + AI answer check for up to 10 keywords on 1 AI engine. Price: $0.70 USDC per call on Base, paid with x402; not charged if the call fails.

  • serp_ai_monitor_deep

    SERP + AI answer check for up to 25 keywords on all AI engines. Price: $2.50 USDC per call on Base, paid with x402; not charged if the call fails.

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "exepal": {
      "type": "http",
      "url": "https://api.exepal.com/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http exepal https://api.exepal.com/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://api.exepal.com/mcp as a custom connector in the settings.

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.