Connect

8 clients · secrets stay placeholders

JSON (mcpServers)Claude CodeCodexOpenCodeCursorVS CodeGemini CLIGoose

{
  "mcpServers": {
    "benchmark": {
      "type": "http",
      "url": "https://benchmark.useimagine.ai/api/mcp",
      "headers": {
        "Authorization": "Bearer ${BENCHMARK_TOKEN}"
      }
    }
  }
}

claude mcp add --transport http benchmark https://benchmark.useimagine.ai/api/mcp --header "Authorization: Bearer ${BENCHMARK_TOKEN}"

[mcp_servers.benchmark]
url = "https://benchmark.useimagine.ai/api/mcp"
bearer_token_env_var = "BENCHMARK_TOKEN"

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "benchmark": {
      "type": "remote",
      "url": "https://benchmark.useimagine.ai/api/mcp",
      "enabled": true,
      "headers": {
        "Authorization": "Bearer {env:BENCHMARK_TOKEN}"
      }
    }
  }
}

{
  "mcpServers": {
    "benchmark": {
      "type": "http",
      "url": "https://benchmark.useimagine.ai/api/mcp",
      "headers": {
        "Authorization": "Bearer ${BENCHMARK_TOKEN}"
      }
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=benchmark&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vYmVuY2htYXJrLnVzZWltYWdpbmUuYWkvYXBpL21jcCIsImhlYWRlcnMiOnsiQXV0aG9yaXphdGlvbiI6IkJlYXJlciAke0JFTkNITUFSS19UT0tFTn0ifX0%3D"
}

{
  "servers": {
    "benchmark": {
      "type": "http",
      "url": "https://benchmark.useimagine.ai/api/mcp",
      "headers": {
        "Authorization": "Bearer ${BENCHMARK_TOKEN}"
      }
    }
  }
}

{
  "mcpServers": {
    "benchmark": {
      "httpUrl": "https://benchmark.useimagine.ai/api/mcp",
      "headers": {
        "Authorization": "Bearer ${BENCHMARK_TOKEN}"
      }
    }
  }
}

extensions:
  "benchmark":
    enabled: true
    name: "benchmark"
    type: streamable_http
    uri: "https://benchmark.useimagine.ai/api/mcp"
    headers:
      "Authorization": "Bearer ${BENCHMARK_TOKEN}"
    timeout: 300

Placeholders to fill from your own secret store: ${BENCHMARK_TOKEN}. The registry never accepts secret values.

Quality 85 / 100good

protocol75 · weight 25

warn
protocol.modernnewest supported version is 2025-06-18; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
n/a
protocol.statelessonly applies to 2026-07-28 servers
pass
protocol.transportstreamable HTTP
n/a
protocol.list_ttlonly applies to 2026-07-28 servers

authorizationn/a · weight 15

n/a
auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
n/a
auth.secret_in_urlno templated URL

tool hygiene86 · weight 30

pass
tools.descriptionsevery tool has a description
pass
tools.description_lengthdescriptions are concise
pass
tools.schemasevery tool has an object input schema
pass
tools.annotations5 of 5 tools declare readOnlyHint or destructiveHint
fail
tools.directory_hintsno tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: list_companies (destructiveHint, idempotentHint, openWorldHint); company_fit_summary (destructiveHint, idempotentHint, openWorldHint); industry_landscape (destructiveHint, idempotentHint, openWorldHint); …
pass
tools.token_costabout 1,212 tokens to load every tool
pass
tools.api_dumptools are not a one-to-one API dump

stability100 · weight 15

pass
stability.changes5 tool changes in 30 days
pass
stability.rug_pullno tool changed its meaning under the same name

dependenciesn/a · weight 15

n/a
deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

5 tools, about 1,212 tokens to load them all · tool set 3d9587936ac9 · tools last changed 2026-10-17 · checked 2026-10-20 11:08 UTC

Tool changes

2026-10-17company_fit_summarychangeddescription
before
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. Company score = median of its 5 most active fitted people (by original posts in the last 90 days) plus the company page. With exactly one fitted account (a person or the page) the company ranks on that account's own fit, flagged "1 account"; it is held back while teammates still await their history pull. people.counted / countedPersonIds say who is in. Use for 'how is X doing on LinkedIn'.
after · 84% of words in common
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. Company typical post = median over up to 5 counted fitted people plus the company page: founders, CEO and C-suite who posted in the last 90 days first, then the most active fitted people (by original posts in that window). With exactly one fitted account (a person or the page) the company ranks on that account's own fit, flagged "1 account"; it is held back while teammates still await their history pull. people.counted / countedPersonIds say who is in. Use for 'how is X doing on LinkedIn'.
2026-10-15industry_landscapechangeddescription
before
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). Public callers get bands and pooled lifts, the same as Discover. Use for "what works in fintech" or "where does X sit in its market".
after · 93% of words in common
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, solo = "1 account" when one fitted account carries the company), population vs the research baseline, and category lift with the author effect removed (which post types beat each author's own typical post). Public callers get bands and pooled lifts, the same as Discover. Use for "what works in fintech" or "where does X sit in its market".
2026-10-15company_fit_summarychangeddescription
before
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. Company score = median of its 5 most active fitted people (by original posts in the last 90 days) plus the company page; needs 2+ fitted accounts. people.counted / countedPersonIds say who is in. Use for 'how is X doing on LinkedIn'.
after · 66% of words in common
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. Company score = median of its 5 most active fitted people (by original posts in the last 90 days) plus the company page. With exactly one fitted account (a person or the page) the company ranks on that account's own fit, flagged "1 account"; it is held back while teammates still await their history pull. people.counted / countedPersonIds say who is in. Use for 'how is X doing on LinkedIn'.
2026-10-13industry_landscapechangedinput schema
2026-10-13list_companieschangedinput schema

Full history: list_changes · trend: quality JSON.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.

Trust 83 / 100

no-repository

provenance55

liveness100

freshness100

hygiene80

+dns-namespace +website +reachable +uptime-100% +updated-10d-ago -no-repository

Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.

Endpoints

remote	auth	reachable	uptime 30d	p50	protocol	last ok
`https://benchmark.useimagine.ai/api/mcp` streamable-http	none	yes	100%	409 ms	2025-06-18	2026-10-20

Tools (5)

`category_breakdown`read-only	Post counts and engagement per content category (product update, hiring, personal story, industry insight, ...) for companies or people.
`company_fit_summary`read-only	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. Company typical post = median over up to 5 counted fitted people plus the company page: founders, CEO and C-suite who posted in the last 90 days first, then the most active fitted people (by original posts in that window). With exactly one fitted account (a person or the page) the company ranks on that account's own fit, flagged "1 account"; it is held back while teammates still await their history pull. people.counted / countedPersonIds say who is in. Use for 'how is X doing on LinkedIn'.
`industry_landscape`read-only	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, solo = "1 account" when one fitted account carries the company), population vs the research baseline, and category lift with the author effect removed (which post types beat each author's own typical post). Public callers get bands and pooled lifts, the same as Discover. Use for "what works in fintech" or "where does X sit in its market".
`list_companies`read-only	List companies in the benchmark catalog (customers, competitors, industry peers). Filter by name substring, industry, or tracking. Returns ids you pass to every other tool.
`methodology`read-only	Imagine AI research rules (log-normal engagement, geometric means, research baseline 49/77/130). Call once before interpreting any numbers.

Schemas: list_tools.

Similar MCP servers

Official server.json

{
  "name": "ai.useimagine/benchmark",
  "title": "Imagine AI Benchmark",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://benchmark.useimagine.ai/api/mcp",
      "type": "streamable-http",
      "headers": [
        {
          "name": "Authorization",
          "isSecret": true,
          "description": "Optional. Bearer <workspace agent key> for post-level data. Public aggregate tools work without it."
        }
      ]
    }
  ],
  "version": "0.1.0",
  "websiteUrl": "https://benchmark.useimagine.ai",
  "description": "LinkedIn content benchmark for 900+ B2B companies and their teams, with an open scoring method."
}