@esaio/esa-mcp-server
npm
v0.14.0
Source verified
Published by esaio — publish provenance cryptographically ties this package to that repository. That is proof of origin, not an official vendor package.
Official MCP server for esa.io - STDIO transport version
The grade answers one question — how safe is this server for you to adopt — so it is computed in two auditable stages. Nothing below is an opinion or an LLM's guess; every line is a real term the deterministic engine applied, and the same input always yields the same number.
1. Threat score — 100 − 6.3 = 94. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −6.3 | Near-miss of exa-mcp-server MTC-SUP-005 | supply-chain |
2. Client adoption risk — 94 − 3 = 91. Three small, subtract-only factors that reflect your risk in adopting it — a clean scan proves less on a powerful, unverified or barely-inspectable package, so the grade says so plainly:
| Points | Adoption-risk factor |
|---|---|
| −3 | capability blast radius (moderate) — client exposure if the model is manipulated |
Capability observations and info notes are shown under Findings but never scored.
Open any row's finding below for the file, line and evidence behind a deduction.
Untrusted-input tools ([esa_get_post]) co-exist with external-action tools ([esa_create_comment, esa_get_markdown_syntax_help]). A prompt injection could cause unwanted external actions, though no direct sensitive-data leak path was found.
Evidence: untrusted [esa_get_post] → sinks [esa_create_comment, esa_get_markdown_syntax_help]
Fix: Require confirmation for state-changing/egress actions triggered after processing untrusted content.
Location: flow esa_get_post → esa_create_comment
"@esaio/esa-mcp-server" is edit-distance 1 from the package "exa-mcp-server" (keyboard-adjacent slip). Verify this is the intended package.
Fix: Confirm you meant "exa-mcp-server". Install packages only from their documented, official name.
Location: package @esaio/esa-mcp-server
Each tool and what it can reach — statically extracted from the published source.
esa_create_commentnetwork egressesa_get_markdown_syntax_helpnetwork egressesa_get_postingests untrusted inputesa_append_postno sensitive capabilityesa_archive_postno sensitive capabilityesa_create_postno sensitive capabilityesa_delete_commentno sensitive capabilityesa_duplicate_postno sensitive capabilityesa_get_all_category_pathsno sensitive capabilityesa_get_attachmentno sensitive capabilityesa_get_categoriesno sensitive capabilityesa_get_commentno sensitive capabilityesa_get_post_backlinksno sensitive capabilityesa_get_post_commentsno sensitive capabilityesa_get_search_options_helpno sensitive capabilityesa_get_team_commentsno sensitive capabilityesa_get_team_membersno sensitive capabilityesa_get_team_statsno sensitive capabilityesa_get_team_tagsno sensitive capabilityesa_get_teamsno sensitive capabilityesa_get_top_categoriesno sensitive capabilityesa_prepend_postno sensitive capabilityesa_rollback_post_revisionno sensitive capabilityesa_search_helpno sensitive capabilityesa_search_postsno sensitive capabilityesa_ship_postno sensitive capabilityesa_update_commentno sensitive capabilityesa_update_postno sensitive capabilityCross-tool combinations that form a data-exfiltration primitive (untrusted input → sensitive source → external sink).
Scan history per published version. The engine is deterministic — the same version always yields the same score, so a changed score means the package itself changed.
| Version | Score | Findings | Engine | Scanned |
|---|---|---|---|---|
v0.14.0 latest |
A 91/100 | 2 | 1.13.0 | 2026-09-07 |
v0.13.0 |
A 91/100 | 2 | 1.12.1 | 2026-08-18 |
Show this server's live Trust Score in your README, docs or website. The badge is served straight from the registry and updates automatically after every rescan — no API key needed. It links back to this page, so anyone who sees the grade can also read the findings behind it instead of taking a number on faith.
The score above is reproducible: the same package version always yields the same result. Run it locally or over the free API — no account, no LLM, fully deterministic.
npx mcptrustchecker scan @esaio/esa-mcp-server --online
Independent packages implementing the same tool, scanned with the same engine. Compare all 5 side by side →
ESA MCP Server - Modular Alibaba Cloud ESA tools for Edge Routine, Pages, and Site management
[](https://github.com/koki-develop/esa-mcp-server/releases/latest) [](./LICENSE) [. Functional API with dry-run support.
MCP server layer exposing agent-mesh orchestrator as an MCP agent