mcp@1.0.14

VERIFIED

Publisher claims: "Official Model Context Protocol (MCP) server for SlashML (Claude Desktop, Claude Code, OpenAI Codex, Cursor, Windsurf, Cline, Zed)" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher slashml · publishing for 19 daysInstalls 2,898Last detonated 1 h ago
$claude mcp add mcp -- npx -y @slashml/mcp
WatchReport an issue

Coverage

Server started and answered tools/list.
Tested
MCP initialize and tools/list · every tool description, for hidden instructions · every file read, file written and host contacted by what ran
Not tested
what the tools do when called with real credentials

Before you give it your token

It will ask for
ELLIPSIS_API_TOKENELLIPSIS_SESSION_TOKENHINDSIGHT_API_KEYHONCHO_API_KEYLETTA_API_KEYMEM0_API_KEYSLASHML_API_KEYSUPERMEMORY_API_KEYZEP_API_KEYConfiguration, not credentials: ELLIPSIS_API_URL, ELLIPSIS_SESSION_ID, HERMES_HOME, NODE_TEST_CONTEXT, PYTEST_CURRENT_TEST, SLASHML_AGENT_ID, SLASHML_BASE_URL, SLASHML_CONSOLE_URL, SLASHML_DISABLE_AUTO_HOOKS, SLASHML_FORCE_AUTO_HOOKS, SLASHML_HOOK_STATE_PATH, SLASHML_MODEL, SLASHML_PASSIVE_WRITES, SLASHML_PROJECT_ID, SLASHML_REDACT_POLICY, SLASHML_REDACT_SCOPE, SLASHML_SANDBOX_INTERVENTION_PATH, SLASHML_SANDBOX_OFFSETS_PATH, SLASHML_SANDBOX_PID_PATH, SLASHML_SESSION_ID, SLASHML_TELEMETRY_PATH, SLASHML_TRANSCRIPT_DIR, SLASHML_USER_ID
Where it talks to
slashml.ai (its own)Also ellipsis.dev, mem0.ai, getzep.com, supermemory.ai, honcho.dev, vectorize.io, letta.com — 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 real credentials

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names ellipsis.dev, mem0.ai, getzep.com, supermemory.ai, honcho.dev, vectorize.io, letta.com as well as its own vendor. The guard injects ELLIPSIS_API_TOKEN, ELLIPSIS_SESSION_TOKEN, HINDSIGHT_API_KEY, HONCHO_API_KEY, LETTA_API_KEY, MEM0_API_KEY, SLASHML_API_KEY, SUPERMEMORY_API_KEY, ZEP_API_KEY only into requests to slashml.ai (and its subdomains) and refuses the rest.

$vet-skills run --secrets ELLIPSIS_API_TOKEN=slashml.ai,ELLIPSIS_SESSION_TOKEN=slashml.ai,HINDSIGHT_API_KEY=slashml.ai,HONCHO_API_KEY=slashml.ai,LETTA_API_KEY=slashml.ai,MEM0_API_KEY=slashml.ai,SLASHML_API_KEY=slashml.ai,SUPERMEMORY_API_KEY=slashml.ai,ZEP_API_KEY=slashml.ai -- npx -y @slashml/mcp

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

What changed since 1.0.13

vet-skills diff mcp 1.0.13 1.0.14

This version reaches for something 1.0.13 did not: 1 new tool (redact_memory). Compared from the two recorded runs, not from source.

New tools
redact_memory

Tool descriptor hashes were not recorded for both runs; renamed or added tools are compared, rewritten descriptions are not.

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-11-16 and scored it 83/100 (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 · 20 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
20sclaimed9 tools: add_memory, search_memories, get_memories, forget_memory, redact_memory, dismiss_intervention, index_repository, search_code_by_behavior, find_bug_candidates
20stools04dc2048de882f2c
20stools6b61845eaaf347f2
20stools2413618b9db6e167
20stoolse3c350819343e5aa
20stools0536997fd3d9d454
20stoolscca81c178a349f14
20stoolsf6f106d66b8ec68c
20stools548eb393d8d8e315
20stoolse5c3dd32631722ce
20sprocessscript backend runs setup only
20sprocessno install scripts to re-run

Static findings

HIGH
Access to sensitive file pathsbin/slashml-mcp.js:167 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesconst envPath = path.join(process.cwd(), ".env");Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
npx invocation of non-well-known packagebin/slashml-mcp.js:480 · npx invocation of non-well-known package — may execute untrusted codemessage: `A 6-digit verification code has been sent to ${checkedEmail}. Ask the user for the 6-digit code and run: npx -y @slashml/memory --verify ${checkedEmail} <6-digit-code>`,Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathsbin/slashml-mcp.js:41 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files--write-env Save SLASHML_API_KEY to .env in the current directoryFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
npx invocation of non-well-known packagebin/slashml-mcp.js:666 · npx invocation of non-well-known package — may execute untrusted codeconst hookCmd = "npx -y @slashml/memory --hook";Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagebin/slashml-mcp.js:489 · npx invocation of non-well-known package — may execute untrusted codethrow new Error("Missing 6-digit verification code. Usage: npx -y @slashml/memory --verify <email> <6-digit-code>");Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathsbin/slashml-mcp.js:352 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesconst envPath = path.join(cwd, ".env");Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
npx invocation of non-well-known packagebin/slashml-mcp.js:26 · npx invocation of non-well-known package — may execute untrusted codeclaude mcp add --scope user ml-memory -e SLASHML_API_KEY="$SLASHML_API_KEY" -- npx -y @slashml/memoryFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagebin/slashml-mcp.js:21 · npx invocation of non-well-known package — may execute untrusted codenpx -y @slashml/memory [options]Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathsbin/slashml-mcp.js:373 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesif (!gi.split(/\r?\n/).some((l) => l.trim() === ".env" || l.trim() === ".env*")) {Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05

Cost to the agent

Instructions loaded
≈67 tok
1 file · 8 in bundle
Tool list per prompt
≈946 tok
9 tools · 105 per tool
Handshake
100 ms
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 118

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 @slashml/mcp@1.0.14 as of 38 min ago. This is the package itself, not its dependencies.