Skills/PyPI/memoryintelligence-mcp

memoryintelligence-mcp@0.2.14

CAUTION· not started

Publisher claims: "DEPRECATED — final release (0.2.14). Use the MemoryIntelligence desktop app's MCP or the claude.ai connector. MCP server for MemoryIntelligence." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher somewhere11 · publishing for 133 daysInstalls 110Last detonated 3d ago
What would fix thisWatchDispute verdict

Coverage

Not started: dependency install failed; the server itself was not observed.
Tested
the dependency install step · every file read, file written and host contacted by what ran
Not tested
server startup · the tool list · tool behavior

What this means for the label: Caution here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

It will ask for
MI_API_KEYMI_SIGNING_PUBKEYConfiguration, not credentials: MI_BASE_URL, MI_BGE_MODEL_PATH, MI_DEFAULT_PII_HANDLING, MI_DEFAULT_RETENTION, MI_DEFAULT_SCOPE, MI_DEFAULT_SOURCE, MI_HOST, MI_KEYCHAIN_ACCOUNT, MI_MCP_FULL, MI_MCP_LOCAL, MI_MCP_OPT_IN_ALL, MI_MCP_STRICT_CWD, MI_PORT, MI_TRANSPORT, MI_VAULT, PIPX_HOME
Where it talks to
memoryintelligence.io (its own)Also githubusercontent.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
server startup · the tool list · tool behavior

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names githubusercontent.com as well as its own vendor. The guard injects MI_API_KEY, MI_SIGNING_PUBKEY only into requests to memoryintelligence.io (and its subdomains) and refuses the rest.

$vet-skills run --secrets MI_API_KEY=memoryintelligence.io,MI_SIGNING_PUBKEY=memoryintelligence.io -- uvx memoryintelligence-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; not started: dependency install failed; the server itself was not observed) on 2026-11-11 and scored it 75/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; Hidden zero-width characters detected; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.1sprocessdependency install exit 1 ·
0.1sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.1sprocessscript backend runs setup only
0.1sprocessno install scripts to re-run

Static findings

HIGH
Access to sensitive file pathssrc/mi_mcp/paths.py:8 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files~/.memoryintelligence/.env on-disk keyfile (chmod 600) — cross-platform fallback to the KeychainFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Process kill commandsrc/mi_mcp/server.py:597 · Process kill command — agent can terminate processes# cold-start latency local reads exist to kill reappears on query #1 (review H1).Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Hidden zero-width characters detectedsrc/mi_mcp/scrub.py:74 · Hidden zero-width characters detected — may conceal content_INVISIBLE = {ord(c): None for c in "​‌‍­⁠"}Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
MEDIUM
Python subprocess execution detectedsrc/mi_mcp/keys.py:58 · Python subprocess execution detectedr = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File permission modification commandsrc/mi_mcp/paths.py:8 · File permission modification command — agent changes file ownership/permissions~/.memoryintelligence/.env on-disk keyfile (chmod 600) — cross-platform fallback to the KeychainFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Access to sensitive file pathssrc/mi_mcp/cli.py:287 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filessrc = "~/.mi-env" if envf.name == ".mi-env" else "~/.memoryintelligence/.env"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedsrc/mi_mcp/cli.py:228 · Python subprocess execution detectedsubprocess.run([claude, "mcp", "remove", key], capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/mi_mcp/config.py:28 · Python subprocess execution detectedr = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/mi_mcp/cli.py:277 · Python subprocess execution detectedr = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File permission modification commandsrc/mi_mcp/paths.py:98 · File permission modification command — agent changes file ownership/permissions"""Preferred on-disk keyfile (``~/.memoryintelligence/.env``, chmod 600) — theFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Access to sensitive file pathssrc/mi_mcp/config.py:19 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesmacOS Keychain (service ``MI_API_KEY``) → keyfile (~/.memoryintelligence/.env, thenFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File permission modification commandsrc/mi_mcp/cli.py:1284 · File permission modification command — agent changes file ownership/permissionsprint(f" [1/4] key → {envf} (chmod 600)")Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Access to sensitive file pathssrc/mi_mcp/cli.py:19 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesor, on Linux/Windows (or by choice), a ``chmod 600 ~/.memoryintelligence/.env``Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File permission modification commandsrc/mi_mcp/cli.py:1136 · File permission modification command — agent changes file ownership/permissions"""Write the key to a ``chmod 600`` ``~/.memoryintelligence/.env`` keyfile.Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Python subprocess execution detectedsrc/mi_mcp/cli.py:222 · Python subprocess execution detectedsubprocess.run([claude, "mcp", "remove", SERVER_KEY], capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File permission modification commandsrc/mi_mcp/cli.py:19 · File permission modification command — agent changes file ownership/permissionsor, on Linux/Windows (or by choice), a ``chmod 600 ~/.memoryintelligence/.env``Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Python subprocess execution detectedsrc/mi_mcp/cli.py:230 · Python subprocess execution detectedr = subprocess.run(add_cmd, capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File permission modification commandsrc/mi_mcp/cli.py:1281 · File permission modification command — agent changes file ownership/permissionsprint(f" [1/4] Keychain unavailable ({e}); key → {envf} (chmod 600) instead")Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Access to sensitive file pathssrc/mi_mcp/cli.py:105 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesecho "run-mi-mcp: MI_API_KEY not found (env, Keychain service 'MI_API_KEY', or ~/.memoryintelligence/.env)" >&2Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/mi_mcp/cli.py:285 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesenvf = paths.resolve_keyfile(home) # new ~/.memoryintelligence/.env, else legacy ~/.mi-envFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/mi_mcp/paths.py:100 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesreturn hidden_home(home) / ".env"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File permission modification commandsrc/mi_mcp/cli.py:1146 · File permission modification command — agent changes file ownership/permissions"# Private (chmod 600). Never commit this file.\n"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Access to sensitive file pathssrc/mi_mcp/paths.py:98 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"""Preferred on-disk keyfile (``~/.memoryintelligence/.env``, chmod 600) — theFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/mi_mcp/cli.py:99 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesfor __mi_envf in "$HOME/.memoryintelligence/.env" "$HOME/.mi-env"; doFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedsrc/mi_mcp/cli.py:224 · Python subprocess execution detectedg = subprocess.run([claude, "mcp", "get", key], capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/mi_mcp/keys.py:70 · Python subprocess execution detectedr = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
System prompt continuationCHANGELOG.md:421 · System prompt continuation — attempts to append to system instructions · informational: not an instruction fileinstruction:Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Prompt injection attemptCHANGELOG.md:428 · Prompt injection attempt — 'ignore previous instructions' · informational: not an instruction file`[/INST]`, `<<SYS>>`) and high-signal override phrases ("ignore previousFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injection attemptCHANGELOG.md:427 · Prompt injection attempt — model control tokens · informational: not an instruction file(`System:` / `Assistant:` / …), chat-template sentinels (`<|im_start|>`,Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01

Cost to the agent

Instructions loaded
≈78 tok
1 file · 23 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

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 memoryintelligence-mcp@0.2.14 as of 3d ago. This is the package itself, not its dependencies.

What would make this Verified

5 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim somewhere11: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  3. Hidden zero-width characters detected≈ +4 on the totalKeep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
  4. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  5. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  6. File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim somewhere11Propose a patch to the maintainer