Skip to content

DataEcho MCP server

Which MCP servers are DataEcho'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 2026-10-23

← Back to DataEcho

Whose server it is
  • Registry nameai.dataecho/mcpverified in the MCP registry

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

When we asked itchecked 2026-10-23
  • Stateanswerschecked 2026-10-23
  • Tools26
  • Server calls itselfdataecho
  • Server version1.0.0
  • Protocol version2025-06-18

On 2026-10-23 the server answered initialize and tools/list without a sign-in. First answer in 194 ms.

Should an agent connect itNot proven either way yet
  • Its tools do every use case we checked: publish a static HTML page to a live URL; keep agent memory on a private versioned drive.
  • Checked on 5 of the 7 days it takes to judge reliability.

Once connected

  • For "publish a static HTML page to a live URL", the likely first call is publish_site.
  • For "keep agent memory on a private versioned drive", the likely first call is platform_info.
  • publish_site, update_site_metadata, delete_site, create_drive, drive_write_file change data without a sign-in: anyone with the address can call them.

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: 5, the first on 2026-10-23
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 5 so far
  • What an agent can do with it2 of 2 use cases
  • Answeredmeasuring5 of the 7 daily checks it takes to print a share
  • Median first answer536 ms
  • Space in an agent's context≈ 2,732 tokensthe definitions of all its tools (26), which an agent carries on every turn
  • Tool definitionsB · 83 of 100
  • Typed results0 of 26 toolsdeclared outputSchema: results come typed, read once
  • Not saying whether it only reads or can destroy: 26 of 26

What an agent can do with it

  • can do · publish a static HTML page to a live URL
  • can do · keep agent memory on a private versioned drive
  • not sure · run a Dockerfile app in a sandboxed container

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

  • Tools that change data, on a server that answers without a sign-in: publish_site, update_site_metadata, delete_site, create_drive, drive_write_file

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 offers26 tools · read 2026-10-23
  • platform_info

    DataEcho platform overview: what it can host, auth state of this connection, docs links. Call this first if unsure.

  • request_login_code

    Start sign-in: email a one-time code to the user. Follow with verify_login_code.

  • verify_login_code

    Complete sign-in with the emailed code. Returns the apiKey ONCE — configure it as the `Authorization: Bearer <key>` header of this MCP connection (and/or save to ~/.artifact/credentials for the CLI scripts). Never echo it into chat.

  • publish_site

    Deploy files to a live URL. No slug → create a NEW site (works without auth; anonymous sites expire in 24h — always show the user the claimUrl). With slug → UPDATE that site (complete snapshot: send ALL files). A Dockerfile in the files…

  • claim_site

    Make a previously-anonymous site permanent under the authenticated account (requires auth + the claimToken from publish_site).

  • list_sites

    List all sites owned by the authenticated account.

  • search_sites

    Full-text search across the authenticated account's sites (names, metadata, and text content).

  • get_site

    Full details + current file manifest of an owned site.

  • update_site_metadata

    Patch site settings without redeploying: viewer title/description, SPA mode, TTL, password (string sets, null removes).

  • delete_site

    Permanently delete an owned site. Irreversible — confirm with the user first.

  • app_status

    Build/run status of a container app deployed via publish_site with a Dockerfile. Poll until status is `live` or `failed`.

  • list_drives

    List the authenticated account's private cloud drives.

  • create_drive

    Create a new private drive.

  • drive_list_files

    List files in a drive (by drive name or drv_… id), optionally under a path prefix.

  • drive_read_file

    Read a file from a drive. Text comes back as utf-8 `content`; binary as `contentBase64`. Files over 1 MB are refused (use the skill scripts).

  • drive_write_file

    Write/overwrite one file in a drive (ETag-safe: pass ifMatch to assert the version you read, otherwise the current version is used automatically).

  • drive_delete_file

    Delete one file from a drive.

  • drive_move_file

    Move/rename a file inside a drive.

  • drive_share

    Mint a scoped drive access token for another agent (perms read|write, optional path prefix + TTL like `7d`). The secret is returned ONCE.

  • drive_tokens

    List active share tokens of a drive (secrets are never shown again).

  • drive_revoke_token

    Revoke a drive share token.

  • drive_history

    Version timeline of a drive (every write is a restorable version).

  • drive_restore

    Restore a drive to a prior version (commits a new version; nothing is lost).

  • list_variables

    List account variable NAMES (values are write-only — they are injected into proxy calls and container apps, never read back).

  • set_variable

    Create/update a write-only account secret (uppercase name). Injected as env vars into container apps and as ${VAR} into proxy calls. Optionally pin which upstream hosts may receive it.

  • delete_variable

    Delete an account variable.

How to connect

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

{
  "mcpServers": {
    "dataecho": {
      "type": "http",
      "url": "https://dataecho.ai/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http dataecho https://dataecho.ai/mcp

Add to CursorAdd to VS Code

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

OpenAPI spec

36 paths, read 2026-10-23. 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.