# Apollo Claude Code MCP Evaluation

**Category:** Sales Intelligence
**Score:** 11 (D)

This is the agent-readable Devtool Arena evaluation page for Apollo on Claude Code MCP.

## Summary

| Metric | Value |
|--------|-------|
| Status | completed |
| Overall score | 11 |
| Grade | D |
| Eval score | 0 |
| Discovery score | 38 |
| Cost | $0.45 |
| Runtime | 3m 2s |
| Tool calls | 21 |
| Errors | 1 |
| Tokens used | 352086 |
| Success | No |

## Agent-Readiness Checklist

| Signal | Evidence |
|--------|----------|
| Context7 | Not found |
| llms.txt | Not found |
| MCP server | Not found |
| Typed SDK | Not found |
| OpenAPI | Not found |
| Agent skills | Not found |
| CLI | Not found |

## Evaluation Prompt

````text

# Task
Using the Apollo MCP, run a small B2B prospecting workflow:

1. Discover available MCP tools and their capabilities
2. Run TWO related lookups to build a prospect picture:
   a. Find companies in the "software" / SaaS industry with roughly 200-1000 employees
   b. Find people associated with companies in that same segment, ideally in senior engineering leadership roles (for example "VP of Engineering" or "Head of Engineering")
   Use whichever tools the MCP actually exposes and your credentials are authorized for — a people search, a contact search, or an employees-at-company lookup are all acceptable for step (b). If one tool returns a 403 or an authorization/scope error, do not stop: fall back to the nearest available equivalent and note which one you used.
3. Merge the records from both lookups, deduplicate by a stable identifier (person/company ID, or email or company domain if no ID is available), and rank them to select the top 5 most relevant prospects
4. If the MCP exposes an enrichment or record-detail tool, use it on the single top-ranked prospect to retrieve fuller detail than the list lookup returned
5. Format the output as JSON with two keys:
   - "results": the top 5 deduplicated prospects, each with a "name" (or title) and an "id", "url", or "domain"
   - "enriched": the fetched detail of the top prospect, including its "name" (or title) and "id"

Use ONLY the MCP tools for all lookup and enrichment operations.
Do not send emails, enroll anyone in a sequence, or perform any other outreach action — this is a read-only research workflow.

You MUST use the Apollo MCP server to accomplish this task.
Use the MCP tools for the actual product operations. Do NOT use curl, fetch, raw HTTP requests, CLI commands, or SDK calls as substitutes.

Use the MCP tools' help/descriptions to understand what each tool does.
If you need additional context, check the documentation: https://docs.apollo.io/docs/apollo-mcp

## Setup
Do NOT assume the Apollo MCP server is already installed or already running in this sandbox.
Review the installation and authentication details below before starting the task.

### Installation
Transport: `http`
This MCP server uses `http` transport.
Claude Code should connect to: `https://mcp.apollo.io/mcp`
Do not assume a local MCP package is already installed; the task depends on the remote server being reachable.
Bootstrap notes: Remote Streamable HTTP MCP server; no package install and no local runtime/stdio process required. Registered successfully with the exact documented command and it appears in `claude mcp list`. Transport verified directly: POST https://mcp.apollo.io/mcp returns content-type text/event-stream and an initialize result with protocolVersion 2025-06-18, serverInfo {name: Apollo.io, version: 1.0.0}, capabilities {tools:{listChanged:false}}. No mcp-session-id header is issued. Auth is OAuth 2.1 + PKCE, NOT a bearer token or API key. Unauthenticated calls return 401 with WWW-Authenticate: Bearer realm="Apollo.io", resource_metadata=https://mcp.apollo.io/.well-known/oauth-protected-resource. Therefore bearer_token_env_var is null and required_env_vars is empty.

### Authentication
Authentication method: `oauth_rs_dcr_authcode`
No MCP auth environment variables were provided. Use the documentation if the server reports authentication errors.

## Execution
1. The harness has already written the launch configuration for `apollo`. Start with the task directly; do not rewrite agent settings, `.mcp-runtime.json`, or build a separate MCP client unless the connected server still fails after a normal retry.
2. You do not need to enumerate every MCP tool up front; inspect only the relevant tools you need. Agent-facing MCP tool names may be namespaced like `mcp__apollo__<tool_name>`.
3. Complete the task described above using MCP tools for the actual product operations.
4. If the server fails to start or authenticate, debug the documented setup and retry. Do not fall back to raw HTTP, SDK, CLI, or manual JSON-RPC/MCP calls as a substitute for exposed MCP tools.

Work in the /home/daytona/app directory.
If you use Bash during setup or debugging, limit it to installation/configuration work and then return to MCP tools for the task itself.
If there are errors, debug and fix them until the task runs successfully.

## Summary
When you are done, write a JSON summary file to /home/daytona/app/results.json with this structure:
{
  "operations": [
    {"step": 1, "description": "What you did", "mcp_tool": "tool_name", "success": true/false, "output_summary": "brief result"},
    ...
  ],
  "overall_success": true/false,
  "notes": ["any relevant notes about the execution"]
}

````

## Grader Results

| Check | Passed | Weight | Score | Details |
|-------|--------|--------|-------|---------|
| Task | No | — | — | — |
| Llms Txt | Yes | — | 10 | — |
| Tool Count | No | — | 0 | — |
| Auth Method | Yes | — | 8 | — |
| Official Mcp | Yes | — | 5 | — |
| Output Schema | No | — | 0 | — |
| Tool Stability | Yes | — | 5 | — |
| Tool Description Length | Yes | — | 10 | — |

## Run Artifacts

| Artifact | Value |
|----------|-------|
| Conversation turns | 35 |
| Tool call traces | 21 |
| Generated files | 0 |
| Exit code | — |
| Completed at | 2026-08-21T17:29:50.527574+00:00 |

## Related Pages

- [Claude Code MCP leaderboard](/leaderboard/claudecode/mcp)
- [Compare Claude Code MCP companies](/leaderboard/claudecode/mcp/compare)
- [Agent Landscape](/leaderboard/discoverability)

Canonical URL: https://devtoolarena.com/claudecode/mcp/apollo