Skills/PyPI/sema-mcp

sema-mcp@0.11.0

CAUTION· not started

Publisher claims: "Semantic codebase indexer and MCP server for Claude Code" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher masihmoloodian · publishing for 129 daysInstalls 119Last detonated 1 h ago

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
ANTHROPIC_API_KEYConfiguration, not credentials: HF_HUB_DISABLE_TELEMETRY, SEMA_CHAT_HOME, SEMA_SKIP_CLAUDE, SEMA_SKIP_CODEX, SEMA_SKIP_CURSOR, SEMA_SKIP_GROK, SEMA_SKIP_OPENCODE
Where it talks to
no vendor host named in the codeAlso deepseek.com, openrouter.ai, together.xyz, claude.ai, chatgpt.com, githubusercontent.com, x.ai, opencode.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
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 deepseek.com, openrouter.ai, together.xyz, claude.ai, chatgpt.com, githubusercontent.com, x.ai, opencode.ai as well as its own vendor. The guard injects ANTHROPIC_API_KEY only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- uvx sema-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 2026-11-18 and scored it 68/100 (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; Pipe-to-shell pattern; Pipe-to-shell pattern. 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 pathssema/agent/attachments.py:34 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files".json", ".jsonc", ".yaml", ".yml", ".toml", ".ini", ".cfg", ".conf", ".env",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
CRITICAL
Pipe-to-shell patternsema/cli.py:44 · Pipe-to-shell pattern — downloads and immediately executes remote code"grok": {"binary": "grok", "install": "curl -fsSL https://x.ai/cli/install.sh | bash", "version": ["--version"], "label": "Grok Build"},Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
CRITICAL
Pipe-to-shell patternsema/cli.py:119 · Pipe-to-shell pattern — downloads and immediately executes remote code" curl -fsSL https://raw.githubusercontent.com/masihmoloodian/sema/main/install.sh | sh"Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
HIGH
Direct script execution from GitHub raw URLsema/cli.py:119 · Direct script execution from GitHub raw URL — unverified code source" curl -fsSL https://raw.githubusercontent.com/masihmoloodian/sema/main/install.sh | sh"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
CRITICAL
Pipe-to-shell patternsema/cli.py:38 · Pipe-to-shell pattern — downloads and immediately executes remote code"claude": {"binary": "claude", "install": "curl -fsSL https://claude.ai/install.sh | bash", "version": ["--version"], "label": "Claude Code"},Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
HIGH
Access to sensitive file pathssema/indexer/languages/generic.py:4 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesWorks well for .json, .yaml, .env, .css, .toml, .sh, .sql, and anything elseFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
CRITICAL
Pipe-to-shell patternsema/cli.py:43 · Pipe-to-shell pattern — downloads and immediately executes remote code"opencode": {"binary": "opencode", "install": "curl -fsSL https://raw.githubusercontent.com/opencode-ai/opencode/refs/heads/main/install | bash", "version": ["--version"], "label": "opencode"},Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
MEDIUM
Remote installer piped to shellsema/cli.py:119 · Remote installer piped to shell" curl -fsSL https://raw.githubusercontent.com/masihmoloodian/sema/main/install.sh | sh"Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
HIGH
Access to sensitive file pathssema/indexer/parser.py:18 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files_NAME_REGISTRY: dict[str, ExtractFn] = {} # exact filenames, e.g. ".env", "makefile"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedsema/cli.py:107 · Python subprocess execution detectedelif (pipx := shutil.which("pipx")) and "sema-mcp" in subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsema/cli.py:569 · Python subprocess execution detectedsubprocess.run(["kill"] + pids, check=False)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsema/cli.py:1827 · Python subprocess execution detectedresult = subprocess.run(["pgrep", "-f", "sema serve"], capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Remote installer piped to shellsema/cli.py:44 · Remote installer piped to shell"grok": {"binary": "grok", "install": "curl -fsSL https://x.ai/cli/install.sh | bash", "version": ["--version"], "label": "Grok Build"},Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
Python subprocess execution detectedsema/cli.py:80 · Python subprocess execution detectedresult = subprocess.run(spec["install"], shell=True, check=False)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsema/cli.py:115 · Python subprocess execution detectedresult = subprocess.run(cmd, check=False)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Remote installer piped to shellsema/cli.py:43 · Remote installer piped to shell"opencode": {"binary": "opencode", "install": "curl -fsSL https://raw.githubusercontent.com/opencode-ai/opencode/refs/heads/main/install | bash", "version": ["--version"], "label": "opencode"},Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
Python subprocess execution detectedsema/agent/tools.py:385 · Python subprocess execution detectedproc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsema/cli.py:76 · Python subprocess execution detectedresult = subprocess.run([binary, *spec["version"]], check=False)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsema/cli.py:1674 · Python subprocess execution detectedresult = subprocess.run(["claude", "mcp", "list"], capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Access to sensitive file pathssema/indexer/parser.py:73 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files".env", ".env.local", ".env.development", ".env.production",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Remote installer piped to shellsema/cli.py:38 · Remote installer piped to shell"claude": {"binary": "claude", "install": "curl -fsSL https://claude.ai/install.sh | bash", "version": ["--version"], "label": "Claude Code"},Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
Python subprocess execution detectedsema/cli.py:103 · Python subprocess execution detectedif uv and "sema-mcp" in subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsema/cli.py:274 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsema/cli.py:563 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsema/devops/runner.py:47 · Python subprocess execution detectedproc = subprocess.run(argv, capture_output=True, text=True, timeout=timeout, env=env)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsema/cli.py:1385 · Python subprocess execution detectedresult = subprocess.run(["claude", "mcp", "list"], capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandsema/tui/app.py:782 · Process kill command — agent can terminate processesexcept Exception as exc: # noqa: BLE001 - never kill the app on a bad turnFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedsema/cli.py:257 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Access to sensitive file pathssema/indexer/parser.py:70 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files".env", ".sh", ".bash", ".txt", ".xml", ".graphql", ".sql"],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
≈49 tok
1 file · 65 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 sema-mcp@0.11.0 as of 21 min ago. This is the package itself, not its dependencies.

What would make this Verified

12 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Pipe-to-shell pattern≈ +9 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  2. Unclaimed publisher≈ +8 on the totalClaim masihmoloodian: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. 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.
  4. Direct script execution from GitHub raw URL≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
  5. Remote installer piped to shell≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  6. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim masihmoloodianPropose a patch to the maintainer