Skills/npm/fo-semantic-mcp

fo-semantic-mcp@2.2.2

VERIFIED

Publisher claims: "Model Context Protocol server providing semantic search over Dynamics 365 F&O artifacts." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher xplusplusai · publishing for 391 daysInstalls 419Last detonated 4d ago
$claude mcp add fo-semantic-mcp -- npx -y fo-semantic-mcp
WatchReport an issue

Coverage

Started with a decoy FOINDEX_API_KEY; tool list observed. Tool calls with a real credential not tested.
Tested
server startup with a tagged decoy in FOINDEX_API_KEY · MCP initialize and tools/list · every tool description, for hidden instructions · where the decoy credential went · every file read, file written and host contacted by what ran
Not tested
what the tools do when called with a real credential
Needs
FOINDEX_API_KEY — give it to the server where it runs, through vet-skills run --secrets, so the value never enters the server's environment. Never paste a credential into a chat, a ticket or a report.

Before you give it your token

It will ask for
FOINDEX_API_KEYConfiguration, not credentials: FO_LOCAL_ASSETS_PATH, FO_SEARCH_DEFAULT_LIMIT, FO_SEARCH_DEFAULT_THRESHOLD, FO_SEARCH_MAX_LIMIT, FO_SEARCH_TIMEOUT_MS, FO_SEMANTIC_MCP_NAME, FO_SEMANTIC_MCP_VERSION, FO_THRESHOLD, FOINDEX_DEV_API_URL
Where it talks to
no vendor host named in the codeAlso xplusplus.ai — not the publisher's domain; check what for before connecting.
What the honeypot saw
no credential files read · no network
What we could not test
what the tools do when called with a real credential

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names xplusplus.ai as well as its own vendor. The guard injects FOINDEX_API_KEY only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- npx -y fo-semantic-mcp

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-11-10 and scored it 92/100 (Verified). It did what it claims and nothing else we could detect: no undeclared network egress, no credential reads, no persistent instruction writes. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 50 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
10sprocessdependency install exit 0
30sprocessrelaunched with a decoy FOINDEX_API_KEY (tagged; nothing real)
50sclaimed1 tool with a decoy FOINDEX_API_KEY: search_fo_artifacts
50sprocessscript backend runs setup only
50sprocessno install scripts to re-run

Static findings

MEDIUM
npx invocation of non-well-known packagepackage.json:18 · npx invocation of non-well-known package — may execute untrusted code"build:exe": "npm run build:cjs && npx pkg dist-cjs/server.js --targets node18-win-x64 --output fo-semantic-mcp-win.exe",Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagepackage.json:19 · npx invocation of non-well-known package — may execute untrusted code…de18-win-x64 --output fo-semantic-mcp-win.exe", "bundle": "npm run embed && npx esbuild src/server.ts --bundle --platform=node --target=node18 --outfile=dist/server.bu…Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagepackage.json:20 · npx invocation of non-well-known package — may execute untrusted code"build:exe2": "npm run bundle && npx pkg dist/server.bundle.js --targets node18-win-x64 --output fo-semantic-mcp-win-v2.exe"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Instructions loaded
≈59 tok
1 file · 13 in bundle
Tool list per prompt
≈1,405 tok
1 tool · 1405 per tool
Handshake
542 ms
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 4648

Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.

Known vulnerabilities

No advisories in OSV for fo-semantic-mcp@2.2.2 as of 4d ago. This is the package itself, not its dependencies.