Skip to content
AfterImage logo

AfterImage MCP server

Which MCP servers are AfterImage'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 2026-10-26

← Back to AfterImage

Whose server it is
  • Registry namepage.afterimage/afterimageverified in the MCP registry

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

When we asked itchecked 2026-10-26
  • Stateanswerschecked 2026-10-26
  • Tools2
  • Server calls itselfafterimage
  • Server version0.1.0
  • Protocol version2024-11-05

On 2026-10-26 the server answered initialize and tools/list without a sign-in. First answer in 238 ms.

Should an agent connect itConnect it, with care
  • Its tools do reuse stored page copies to avoid repeat live fetches, but not check current model prices and rate limits.

Once connected

  • For "reuse stored page copies to avoid repeat live fetches", the likely first call is get_page.
  • Parameters are untyped or undescribed in 1 of 2 tools: check arguments before calling.

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: 8, the first on 2026-10-26
  • INITE MCP score81 of 100answers 100 · does the job 50 · definitions 75 · context 100 · connects 100
  • What an agent can do with it1 of 2 use cases
  • Answered100% of days8 of 8 daily checks
  • Median first answer268 ms
  • Space in an agent's context≈ 257 tokensthe definitions of all its tools (2), which an agent carries on every turn
  • Tool definitionsB · 75 of 100
  • Typed results0 of 2 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 1 of 2
  • Not saying whether it only reads or can destroy: 2 of 2

What an agent can do with it

  • not sure · fetch current API documentation pages for an agent
  • cannot · check current model prices and rate limits
  • can do · reuse stored page copies to avoid repeat live fetches

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 offers2 tools · read 2026-10-26
  • get_page

    Return readable text for a public http(s) URL. Reuses a stored copy if it is newer than max_age_s. Includes sha256 hash and fetched_at. Needs a funded API key on this HTTP request.

  • search_pages

    Search pages already stored in AfterImage. Does not visit the live web. Then call get_page for the full text of a hit. Needs a funded API key.

How to connect

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

{
  "mcpServers": {
    "afterimage": {
      "type": "http",
      "url": "https://afterimage.page/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http afterimage https://afterimage.page/mcp

Add to CursorAdd to VS Code

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

OpenAPI spec

7 paths, read 2026-10-26. Open the spec ↗

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.