Skip to main content
Glama
sandcastlelabs

collimer-mcp

by sandcastlelabs
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

collimer-mcp

npm · MIT · Model Context Protocol

⚠️ Retired — switch to the remote server

Collimer is a remote MCP server at https://app.collimer.com/mcp.

Related MCP server: AI Readiness

Use the remote server instead

Claude Code

claude mcp add --transport http collimer https://app.collimer.com/mcp

Claude Desktop — Settings → Connectors → Add custom connector, with the URL https://app.collimer.com/mcp.

Cursor / VS Code / Windsurf / any client that supports remote MCP — in the client's MCP config (~/.cursor/mcp.json, .vscode/mcp.json, .mcp.json):

{
  "mcpServers": {
    "collimer": {
      "type": "http",
      "url": "https://app.collimer.com/mcp"
    }
  }
}

There are no keys to paste. The server speaks OAuth 2.1 with dynamic client registration and PKCE, so your client discovers the endpoints and prompts you to sign in the first time you connect. A free account is enough to connect.

What the remote server does

The remote server exposes the work loop:

  • Scan and audit a brand's AI-search visibility across ChatGPT, Claude, Gemini, Perplexity and Google AI Overviews, and read the finished report.

  • Find the work — open recommendations for a brand in plan-priority order.

  • Do the work — turn a recommendation into a draft for a human to review. It never publishes on its own.

  • Verify the work — check whether what shipped actually landed and moved the score.

  • Onboard a brand end to end, with proposed brand context a person confirms.

If you already have this package installed

Every call fails with a message naming the remote endpoint. Nothing is wrong on your side and there is no version to upgrade to — remove the collimer stdio entry from your MCP config and add the remote server above.

// remove this
{ "collimer": { "command": "npx", "args": ["-y", "collimer-mcp"] } }

What is Collimer?

Collimer measures and improves how often AI answer engines cite your brand — generative engine optimization (GEO), the AI-search successor to SEO. Trackers tell you you're invisible. Collimer gets you cited.

Privacy

The remote server acts on the Collimer account you sign in with. This retired package sent only the domain you passed and an optional email, and read neither your files nor your conversation.

License

MIT © Sandcastle Labs

Available Tools

1 tool
collimer_scanCollimer AI-visibility scanA
Read-only
Inspect

Run a free Collimer scan on a website to measure how visible its brand is in AI search — ChatGPT, Claude, Gemini, Perplexity, and Google AI Overviews. Returns an AI-visibility score (0–100), a confidence interval, the single biggest gap, and a branded report URL. The full ranked fix plan + verification re-scan unlock with a free account on the web. Tip: after the site makes changes, re-run the scan to measure the delta.

ParametersJSON Schema
NameRequiredDescriptionDefault
emailNoOptional — emails the report and speeds claiming the account later.
domainYesThe website to scan, e.g. 'example.com' or 'https://example.com'.

TDQS

A4.1/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare readOnlyHint and openWorldHint, so the description's job is lighter, but it still adds real value: it names the return contents (0–100 score, confidence interval, biggest gap, report URL) and discloses a gating behavior (full ranked fix plan requires a web account). It does not state latency, rate limits, or cost, but for a free read-only scan the added context is solid.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, front-loaded with the core action and immediately followed by what comes back and the free-tier caveat. Every sentence earns its place; the closing tip is a minor extra but useful.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so the description must carry return-value burden, and it does — enumerating the score, confidence interval, biggest gap, and report URL. Combined with annotations covering the read-only/open-world profile, an agent has enough to invoke it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so both parameters (domain, email) are already fully documented in the schema, including the email's optionality and purpose. The description adds no param-level detail, which is the expected baseline when the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Run a free Collimer scan on a website') and what it measures (brand visibility in AI search across named engines). The scope is unambiguous and no sibling tools exist to confuse it with.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear usage context (scan a site to measure AI visibility) and an explicit re-run condition: 'after the site makes changes, re-run the scan to measure the delta.' It also discloses the free-tier boundary (full fix plan unlocks with an account), though no alternative tool exists to route against.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 1 tool updatev0.2.2
    • Removedbeacon_free_scan
  2. 2 tool updatesv0.2.1
    • First observedbeacon_free_scan
    • First observedcollimer_scan
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4.1/5.0

Scored across 1 tool

Disambiguation5/5

There is only one tool, so there is no possibility of the agent confusing it with another. Its purpose (run a brand AI-visibility scan and return a score) is unambiguous.

Naming Consistency5/5

The single name collimer_scan uses a clean snake_case vendor_noun/verb pattern with no competing conventions. Nothing in the set conflicts with it.

Tool Count3/5

A one-tool surface is on the thin side even for a focused scan service, since follow-on actions like re-scanning, comparing deltas, or fetching the full report are alluded to in the description but not exposed. It is defensible as a minimal wrapper, but borderline.

Completeness3/5

The tool covers the core scan action, but the description explicitly defers the ranked fix plan and the verification re-scan to a web account, and there is no way to list past scans or retrieve the report programmatically. That leaves notable gaps around the re-scan/delta workflow the description itself recommends.

Maintenance

ActivityMaintained
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • geo-audit

    nycsav
    A
    license
    Not graded
    quality
    C
    maintenance
    Evaluates any website's AI visibility with 15 checks across crawlability, structure, content, and connectivity, and provides actionable fixes.
    2 npm
    MIT

  • AI Readiness

    epistemedeus
    A
    license
    A
    quality
    C
    maintenance
    Check whether a website is visible to AI search engines (ChatGPT, Perplexity, Claude, Google AI Overviews). Returns a 0-100 readiness score, a grade, and a specific fix for each gap. Dependency-free, no API keys.
    2
    3 npm
    MIT

  • sylgeo-mcp

    hitankshah
    A
    license
    Not graded
    quality
    D
    maintenance
    Enables AI assistants to scan brand visibility across ChatGPT, Claude, Gemini & Perplexity, analyze website GEO readiness, compare competitors, and get actionable recommendations.
    MIT

  • Specularis AI Visibility Audit

    AdevAarons
    A
    license
    Not graded
    quality
    B
    maintenance
    Runs AI visibility (GEO/AEO) audits on websites, checking AI crawler access, schema markup, llms.txt, and content signals, with optional full PDF report.
    MIT