General Tools

useimagine.ai

Provides general-purpose tools through the Model Context Protocol.

1 endpoint5 known toolsFirst detected October 10, 2026Last detected October 10, 2026

ENDPOINT 1

https://benchmark.useimagine.ai/api/mcp

No auth detected

MCP server metadata

Name: imagine-benchmark
Version: 0.1.0

Capabilities

tools

Server instructions

Imagine AI Benchmark: LinkedIn post data for 800+ B2B companies, their founders/execs and competitors (benchmark.useimagine.ai; live counts in the methodology tool). Imagine AI is a content agent built to generate revenue at high-growth companies. It creates coordinated content precisely for your ICP and maps your content to your pipeline and closed revenue. Customer (workspace) keys: call the workspace tool FIRST, every session. It is the live competitor list from the dashboard (own company, current competitors, tracked people); never rely on a cached or hardcoded list, and every comparison tool defaults to that set when you omit companyIds / competitorIds. Start with methodology once per session: engagement is log-normal per account, so compare ACCOUNTS by geometric mean reactions (and x/÷ spread), and judge a POST only against its own account (posts_vs_account). Never rank posts from different accounts against each other on raw numbers. Typical flow: workspace -> competitor_moves / share_of_voice / compare_competitors with no ids (live set) -> posts_vs_account. Catalog flow: list_companies / search_people -> get_company -> account_fits or company_fit_summary -> compare_competitors or industry_landscape -> posts_vs_account for what over/under-performed. Write tools (add_company, add_people, queue_scrape, cancel_run) need a write-scope token and spend scraping credits: only call them when the user asked.

Known tools 5

list_companies

List companies in the benchmark catalog (customers, competitors, industry peers).

Inferred read-only

company_fit_summary

A company's page fit plus the distribution of its people's geometric means (median, baseline band), top people and who is under the 18-post floor.

Potential side effects

industry_landscape

Every account in an industry (or a custom company set): per-company rollup (page fit + people median over the 5 most active fitted people (peopleCounted), preliminary = "Few posts" under 40 team posts), population vs the research baseline, and category lift with the author effect removed (which post types beat each author's own typical post).

Potential side effects

methodology

Imagine AI research rules (log-normal engagement, geometric means, research baseline 49/77/130).

Inferred read-only

category_breakdown

Post counts and engagement per content category (product update, hiring, personal story, industry insight, .

Potential side effects

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.imagine-benchmark]
url = "https://benchmark.useimagine.ai/api/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "imagine-benchmark": {
      "type": "http",
      "url": "https://benchmark.useimagine.ai/api/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: imagine-benchmark
Remote MCP URL: https://benchmark.useimagine.ai/api/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "imagine-benchmark": {
      "url": "https://benchmark.useimagine.ai/api/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "imagine-benchmark": {
      "type": "http",
      "url": "https://benchmark.useimagine.ai/api/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "imagine-benchmark",
  "transport": "streamable-http",
  "url": "https://benchmark.useimagine.ai/api/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.