argus (techwithshadab/argus) is an MCP server listed on the M8ven Trust Index. It scores 74 out of 100, grade C. It declares 26 tools. No publisher has claimed this listing.

Back to MCP Trust IndexM8ven
C
Emerging
74/100
1 day ago

argus

Multi-agent maritime dark-vessel investigation on AWS: Strands and LangGraph agents on Amazon Bedrock AgentCore, MCP tool servers over PostGIS behind a policy-enforcing gateway, a FastAPI watch floor with human review, OpenTelemetry into Grafana and CloudWatch, deployed with CDK.

→ techwithshadab/argus· listed on github_repo_search

Emerging. No concerning findings. Grades remain capped until the project builds reputation through adoption. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

Code Verified⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every pushwhy connect →

Who stands behind it

techwithshadab

Source: github_repo_search

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

⚡ Connect GitHub for Live Monitored

Install from

GitHub

M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.

// key findings
🚨
Secret credentials may flow to a network call
1 flow detected: OPENSANCTIONS_API_KEY. We can’t prove the destination matches the brand the credential belongs to.
🔐
You'll be asked for 4 credentials: DATA_KEY, OPENSANCTIONS_API_KEY, GEMINI_API_KEY, AISSTREAM_API_KEY
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// environment variables
To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.
configCDK_DEFAULT_ACCOUNT
configCDK_DEFAULT_REGION
configSCENARIO_END
configAIS_MODESee .env.example. Notable switches: =live with AISSTREAM_API_KEY for real AIS in the
configOTEL_EXPORTER_OTLP_ENDPOINT
configDEPLOY_ENV
configAUTO_INVESTIGATE_SEVERITIES
configMODEL_PRICES_JSON
configSLO_MAX_COST_PER_INVESTIGATION
configSLO_MIN_EVAL_RECALL
configGIT_SHA
configMCP_SERVER
configMCP_PORT
configTOOL_ALLOWED_ROLES
configTOOL_AUTH
configTOOL_ALLOWED_ACCOUNT
🔐 secretDATA_KEYPersonal data (beneficial_owner, person names) is stored only encrypted with pgcrypto. The key is locally and a KMS-encrypted Secrets Manager secret on AWS (DATA_KEY_SECRET_ARN).
configDATA_KEY_SECRET_ARNPersonal data (beneficial_owner, person names) is stored only encrypted with pgcrypto. The key is DATA_KEY locally and a KMS-encrypted Secrets Manager secret on AWS ().
configAWS_REGION
configPGPASSWORD
configPGPASSWORD_SECRET_ARN
configPGUSER
configPGHOST
configPGPORT
configPGDATABASE
configGEO_USE_OSMthe UI's "watching" selector filters the map per area in both modes); =true for Overpass/Nominatim; OPENSANCTIONS_API_KEY for real
configIMAGERY_OFFLINE
configOPENSANCTIONS_CREDENTIAL_PROVIDER
🔐 secretOPENSANCTIONS_API_KEYthe UI's "watching" selector filters the map per area in both modes); GEO_USE_OSM=true for Overpass/Nominatim; for real
configAPI_URL
configEVAL_API_URL
configEVAL_JUDGE_MODEL
configEVAL_AUTH
configEVAL_TLS_VERIFY
configEVAL_PUSH
configARGUS_NO_REGISTRY
configARGUS_REGISTRY_ID
🔐 secretGEMINI_API_KEYGoogle AI Studio key
configMODEL_IDMODEL_PROVIDER + MODEL_ID; see [Model providers](#model-providers)
configSERVICE_VERSION
configOTEL_CONSOLE
configAGENT_OBSERVABILITY_ENABLED
configARGUS_OTLP_ENDPOINT
configSCENARIO_FILE
configREPLAY_SPEED
configREPLAY_LOOP
configREPLAY_LOOP_PAUSE_S
configPRELOAD_HISTORY
configAREAS_FILE
configEXTRA_DATABASES
🔐 secretAISSTREAM_API_KEYcp .env.example .env # set MODEL_PROVIDER + its credential, optionally an
configWORKER_QUEUE_KIND
configJOB_BACKEND
configJOB_SWEEP_QUEUE_URL
configOFFICER_AUTH
configOIDC_SIGNER
configOIDC_ISSUER
configREVIEW_METRICS
configORCHESTRATOR_MODE
configORCHESTRATOR_URL
configORCHESTRATOR_RUNTIME_ARN
configWORKER_CONCURRENCY
configSWEEP_INTERVAL_MIN
configSWEEP_HOURS
configA2A_WATCH_URL
configA2A_AUTH
configA2A_WATCH_URL_PARAM
configJOB_HEARTBEAT_S
configJOB_REAP_GRACE_S
configARCHIVE_BUCKET
configARCHIVE_DIR
configARCHIVE_PREFIX
configARCHIVE_KMS_KEY_ID
configDRY_RUN
configHOT_DAYS
Deployment configuration, supplied by whoever hosts the server. Users are not asked for these.
deployPORT
deployREDIS_URL
deployDATABASE_URL
// quality suggestions

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

26/26 tools missing one or more hints — raise_alert (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); dismiss_candidate (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_vessel_track (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +23 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

License file

No license file

Add a LICENSE file (MIT, Apache-2.0, etc.).

Tool test coverage

18/26 tools referenced in tests (69%)

Write tests that reference each tool by name so every tool has at least one test.

Secrets not logged

2 secret values sent to log.info/print

Redact or omit secret values from log output.

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail
The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.
// improvement guidance — verified publishers only
We have 5 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Score](https://m8ven.ai/badge/mcp/techwithshadab/argus)](https://m8ven.ai/mcp/techwithshadab/argus)
Shows your grade and updates automatically. Prefer no grade? Append ?variant=verified to the badge URL.
commit: 963c3004cd1dd216aab8adb5dffd3245271ba0ef
code hash: ef52956656f0fe59bd977f4b284adf844f398de10dc17b0fe3b67e2c4b4b42c5
verified: 9/9/2026, 11:21:19 AM
view raw JSON →
Check MCPs from inside your assistant
Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check
check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern
How to add it →Free · no account needed · works in any MCP client