video-research-mcp@0.7.1
CAUTION· startup onlyPublisher claims: "MCP server for video analysis, document extraction, cited research and optional knowledge storage" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Startup only; authenticated tool behavior not tested.- Tested
- server startup over stdio (initialize sent) · every file read, file written and host contacted by what ran
- Not tested
- the tool list (the server exited before answering) · what the tools do when called with real credentials
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
COHERE_API_KEYGEMINI_API_KEYINFRA_ADMIN_TOKENOPENAI_API_KEYS2_API_KEYSEMANTIC_SCHOLAR_API_KEYWEAVIATE_API_KEYYOUTUBE_API_KEYConfiguration, not credentials: CLEAR_CACHE_ON_SHUTDOWN, DEEP_RESEARCH_AGENT, DOC_MAX_DOWNLOAD_BYTES, FLASH_SUMMARIZE, GEMINI_CACHE_DIR, GEMINI_CACHE_TTL_DAYS, GEMINI_CONTEXT_CACHE_TTL, GEMINI_FLASH_MODEL, GEMINI_MAX_SESSIONS, GEMINI_MODEL, GEMINI_RETRY_BASE_DELAY, GEMINI_RETRY_MAX_ATTEMPTS, GEMINI_RETRY_MAX_DELAY, GEMINI_SESSION_DB, GEMINI_SESSION_MAX_TURNS, GEMINI_SESSION_TIMEOUT_HOURS, GEMINI_TEMPERATURE, GEMINI_THINKING_LEVEL, GEMINI_TRACING_ENABLED, INFRA_MUTATIONS_ENABLED, LOCAL_FILE_ACCESS_ROOT, MLFLOW_EXPERIMENT_NAME, MLFLOW_TRACKING_URI, RERANKER_ENABLED, RERANKER_PROVIDER, RESEARCH_DOCUMENT_MAX_SOURCES, RESEARCH_DOCUMENT_PHASE_CONCURRENCY, VIDEO_OUTPUT_DIR, WEAVIATE_AUTO_MIGRATE, WEAVIATE_OLLAMA_API_ENDPOINT, WEAVIATE_OLLAMA_MODEL, WEAVIATE_URL- Where it talks to
- no vendor host named in the codeAlso google.com, semanticscholar.org, youtube.com, astral.sh, docker.internal — not the publisher's domain; check what for before connecting.
- What we saw when it ran
- no credential files read · no network
- What we could not test
- the tool list (the server exited before answering) · 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 google.com, semanticscholar.org, youtube.com, astral.sh, docker.internal as well as its own vendor. The guard injects COHERE_API_KEY, GEMINI_API_KEY, INFRA_ADMIN_TOKEN, OPENAI_API_KEY, S2_API_KEY, SEMANTIC_SCHOLAR_API_KEY, WEAVIATE_API_KEY, YOUTUBE_API_KEY only into requests to the host you bind (and its subdomains) and refuses the rest.
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; startup only; authenticated tool behavior not tested) on 2026-11-20 and scored it 69/100 (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; Access to sensitive file paths; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 20 s · 2 scenariosStatic findings
* Template for ~/.config/video-research-mcp/.env.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.'# - This file is stored in your user config dir (chmod 600 recommended)',Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts."""Parse a ``.env`` file into a dict of key-value pairs.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.Usage: npx video-research-mcp@latest [options]Fix: Pin versions and sources; vendor anything fetched at install time.path: Path to the ``.env`` file.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.raise ValueError("No Gemini API key — set GEMINI_API_KEY or pass api_key explicitly")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.``~/.config/video-research-mcp/.env`` when they aren't alreadyFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.Loads ``~/.config/video-research-mcp/.env`` before reading env vars.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.* Ensure ~/.config/video-research-mcp/.env exists with a commented template.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.const envPath = path.join(envDir, '.env');Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.proc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.proc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.path: Path to the ``.env`` file. Defaults to :data:`DEFAULT_ENV_PATH`Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.ui.step(' ~/.config/video-research-mcp/.env');Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.DEFAULT_ENV_PATH = Path.home() / ".config" / "video-research-mcp" / ".env"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.Cost to the agent
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
Not checked against OSV yet; the weekly check has not reached this version.
What would make this Verified
11 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Reads credential files≈ +27 on the totalThe sandbox saw reads under ~/.ssh, ~/.aws, ~/.npmrc, ~/.config or similar. Read only files inside the project, and only the ones the task needs. Seen: ~/.config/video-research-mcp/.env.
- Unclaimed publisher≈ +8 on the totalClaim galbaz1: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Touches files outside the project≈ +7 on the totalKeep reads and writes inside the working directory, or declare the exact paths in `filesystem:` and explain why in the README.
- 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.
- Credential pass-through configuration≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.