# @echothread/mcp

Read and moderate your EchoThread site comments: pending queue, approve, reject, spam, reply.

- **Type:** MCP server
- **Trust:** 85/100 (A), scored on the package rubric
- **Verification:** verified (build provenance)
- **Version:** 0.1.0
- **Author:** io.echothread
- **License:** MIT
- **npm:** @echothread/mcp
- **Source:** https://github.com/ryabinski-labs/echothread-integrations
- **Compatible clients:** claude-code, cursor, copilot, gemini (basis: transport)

## Trust

85/100 (A), scored on the package rubric
- Publisher verified: no
- Build provenance: verified attestation
- npm trusted publishing (OIDC): yes
- Install scripts: nothing suspicious found
- Prompt-injection scan: not run
- Obfuscation scan: not run
- Evidence age: 0 days

## Security scan

- **Status:** clean
- **Scanned:** 2026-10-10T22:28:15.522Z
- **Version scanned:** 0.1.0
- **CVEs:** none found by OSV at scan time

## Tools

11 declared. Statically extracted from the shipped source — a floor on the surface, not a census.
- `list_sites` — List the sites this token can see, with their ids.
- `list_pending` — List the comments on one site that are waiting for review, oldest first, 50 per page.
- `list_recent_comments` — List comments created since a time across every site this token can see. Needs the Starter plan.
- `get_thread` — Get one thread (a page with comments) and its first page of comments.
- `get_comment` — Get one comment by id.
- `site_stats` — Count a site's comments by status over the last 7 and 30 days.
- `approve_comment` — Approve a comment so it shows on the site. Needs the moderate scope.
- `reject_comment` — Reject a comment so it stays hidden. Needs the moderate scope.
- `mark_spam` — Mark a comment as spam, which hides it and trains the spam filter. Needs the moderate scope.
- `reply_to_comment` — Post a reply to a comment as the site owner. The reply is published straight away. Needs the reply scope.
- `delete_comment` — Permanently delete a comment and its replies. This cannot be undone. Needs the delete scope.

## Install

**Verdict: install** — No blocking findings and no open coverage gaps — safe to install as configured.
**Config** (claude-code):
```json
"{\n  \"mcpServers\": {\n    \"mcp\": {\n      \"command\": \"npx\",\n      \"args\": [\n        \"-y\",\n        \"@echothread/mcp\"\n      ],\n      \"env\": {\n        \"ECHOTHREAD_API_TOKEN\": \"<YOUR_ECHOTHREAD_API_TOKEN>\"\n      }\n    }\n  }\n}"
```
**Credentials it will ask for** (names only — Forge never holds a value):
- `ECHOTHREAD_API_TOKEN` — Echothread API Token (required)
Placeholders only. Forge never holds, brokers, or transmits a credential value — replace each <YOUR_NAME> in your own config file. Do not send a value back to Forge; no Forge endpoint accepts one.
- This entry needs 1 credential (1 required). The generated config carries placeholders, so it will fail in the editor rather than at runtime if they are left unset.

## Blast radius

Extensive blast radius — deletes data; holds an api key.
- Floor 52, ceiling 52 (tier: extensive)
- This is impact, not likelihood. A high radius is not a defect: a filesystem server is supposed to write files. It is never part of the trust score.

## Machine-readable views of this entry

- Signed JSON: https://forgeregistry.com/api/v1/packages/%40echothread%2Fmcp
- Install plan: https://forgeregistry.com/api/v1/packages/%40echothread%2Fmcp/install-plan
- Alternatives: https://forgeregistry.com/api/v1/alternatives/%40echothread%2Fmcp
- HTML page: https://forgeregistry.com/registry/%40echothread%2Fmcp
- MCP: POST https://forgeregistry.com/api/mcp → `forge_get_package` / `forge_install_plan`

## About this document

Generated by Forge (https://forgeregistry.com) — a compact rendering of the same record served, signed, at the JSON URL above. Trust and scan facts are the registry's own measurements; anything Forge did not measure is named as unmeasured rather than omitted.