"namespace:ai.v-safe" matching MCP tools:

• osv_query_package

  osv-advisory-mcp-server

  Query known vulnerabilities for a single package version across any supported ecosystem. Returns all matching OSV advisories with severity (CVSS vectors), CVE aliases, affected version ranges, and first safe version. Use osv_list_ecosystems to validate the ecosystem string before querying — ecosystem strings are case-sensitive exact matches and an invalid value returns an error, not empty results.

  Connector

• list_planned_services

  Sats4AI - Bitcoin-Powered AI Tools

  List all planned services with current vote counts. Returns JSON array: [{ slug, name, description, votes }], sorted by votes descending. No payment required — this is a free discovery tool. Use the slug values with vote_on_service to cast votes. This tool is idempotent and safe to call repeatedly.

  Connector

• taskbounty_security_check

  TaskBounty

  Scan a PUBLIC GitHub repo for GitHub Actions + CI security/maintenance hygiene before launch — ideal for apps built with Lovable, Bolt, Replit, Cursor, or v0 ("is my AI-built app safe to ship?"). Returns a safe summary: findings by category with counts, an unlisted report URL, and fix options. SCOPE, honestly: it checks GitHub Actions workflow + update-automation hygiene only — it does NOT check exposed secrets, auth, payments, webhooks, or runtime behavior, which need a manual review. No API key required. For PRIVATE repos, tell the user to run `npx taskbounty-check .` locally so their source never leaves their machine.

  Connector

• check_token_safety_pro

  BaseGuard + WalletGuard

  Use this tool when you need the most complete token safety signal and social traction or holder momentum is part of your decision criteria. Input the contract address and chain (Base gives full signals; other chains return holder velocity as unknown). Returns the standard safety verdict plus Farcaster mention count and sentiment (last 24h) and holder growth trend — so you can catch tokens with anomalous momentum or negative social sentiment that on-chain checks alone would miss. Example input: {"contractAddress":"0x4ed4e862860bed51a9570b96d89af5e1b0efefed","chainId":"base"} Example output shape: {"riskScore":12,"recommendation":"SAFE","pro":{"proVerdict":"SAFE","farcaster":{"mentions":14,"sentiment":"positive"},"holderGrowth":{"trend":"rising","change24h":8.2}}}

  Connector

• get_model

  Civitai

  Get full details for a single Civitai model by id — description, type, creator, tags, download/rating stats, and every version with its base model, trigger words and downloadable files. Try id 4201 ("Realistic Vision V6.0 B1", a SFW checkpoint). Defaults Safe-For-Work; nsfw flag is surfaced. Keyless.

  Connector

• get_delivery_estimate

  Custom Blinds Shop

  Estimate when a new order will be dispatched. Production is 5 working days (Mon–Fri, excluding South African public holidays). Returns dispatch_date, production_days, and a plain-language summary safe to share with the customer. Never quote a final delivery date — The Courier Guy transit time varies by location. Call this when a customer asks 'when will it arrive?' to give an honest production timeline.

  Connector

• list_regions

  mcp

  List the regions an app can be created or moved to. Returns the live set of supported regions. Use this before calling init_app or manage_app (action: "move") to validate a region slug, or to present region choices to a user. Returns: { regions: string[] } e.g. { regions: ["us-east-1", "us-west-2"] } Idempotency: Safe to call anytime (read-only operation).

  Connector

• autopilot_status

  squeezeos

  Read-only status of the Sovereign Autopilot (CEO Trader). Returns: active (bool), live_mode (bool), symbols watchlist, min_confidence threshold, Kelly fraction, max concurrent positions, cooldown remaining, active open positions with symbol/side/entry/SL/TP, circuit breaker state, daily P&L, daily trade count. Free — no auth required. Safe for any agent to call at any frequency.

  Connector

• forget_memories

  gateway

  Delete memory entries matching filters. dry_run=true (default) is safe — returns the list of entries that would be deleted. Pinned entries are never forgotten. At least one filter required. Owner only — registered handle + secret required.

  Connector

• check_token_safety

  BaseGuard + WalletGuard

  Use this tool when you need to decide whether a token contract is safe before executing a trade or listing it. Input the contract address and chain. Returns a SAFE/CAUTION/AVOID verdict, risk score (0–100), deployer wallet age, LP lock status, and top-10 holder concentration — so you can reject dangerous tokens before committing funds. For Pump.fun tokens use check_pump_token (faster). For sub-3s bulk screening use check_token_safety_lite. Example input: {"contractAddress":"0x4ed4e862860bed51a9570b96d89af5e1b0efefed","chainId":"base"} Example output shape: {"riskScore":12,"recommendation":"SAFE","confidence":"HIGH","checks":{"deployer":{"walletAgeDays":421,"flag":"OK"},"liquidity":{"lpLocked":true,"flag":"OK"},"holders":{"top10Concentration":18.4,"flag":"OK"}},"processingMs":840}

  Connector

• get_safety_report

  Data Compliance Classifier MCP

  Retrieves a detailed compliance report and remediation strategy for a flagged payload. Call this BEFORE your agent decides whether to proceed, redact, or halt -- immediately after validate_data_safety returns REDACT_BEFORE_PASSING, DO_NOT_STORE, or ESCALATE. Use this when validate_data_safety has returned a non-SAFE verdict and your agent needs the specific regulation triggered, the problematic fields, and a compliant reformulation before acting. Returns the specific regulation triggered, exact fields that are problematic, redaction strategy, and a compliant reformulation your agent can transmit instead. Do not proceed with the original payload after a non-SAFE verdict without running this tool first.

  Connector

• get_call_status

  Call For Me

  Poll the status of a call previously placed with place_call. Returns a CallOutcome with one of these statuses (in roughly likely order): queued/placing/ringing/connected — call still in progress, poll again in a few seconds completed — call finished cleanly, structured result available partial — call finished but some questions unanswered voicemail — recipient was voicemail; identified message left no_answer — recipient never picked up busy — recipient line was busy invalid_number — number is not in service rejected_ai — recipient declined to talk to A.I. (do not retry) needs_user_input — recipient needs info only the user can provide online_only — recipient said the task can only be done online timed_out — call exceeded max duration carrier_failure — telephony provider error (safe to retry later) api_error — internal failure (safe to retry) Always carries a free-form `exit_reason` string suitable for showing the user.

  Connector

• pricetik_group_trip_join

  mcp-server

  Join a group trip session by share code (idempotent — joining twice is safe). Pass an optional displayName so other members see who voted. After joining, the caller can read the session, add candidate options, and vote. Requires an authenticated API key (the membership is owned by the PriceTik account). Pass an Idempotency-Key header to make retries safe.

  Connector

• dev_send

  Arcadia Finance

  DEV ONLY — Sign and broadcast an unsigned transaction using a local private key (PK env var). For production, use a dedicated wallet MCP server (Fireblocks, Safe, Turnkey, etc.) instead of this tool. Takes the transaction object returned by any write.* tool and submits it onchain.

  Connector

• request_pilot_key

  PoolParty Main Stage Airtime

  Request pilot access to PoolParty MCP protected tools. No auth required. Two paths: safe public discovery_submission requests can auto-provision a short-lived submit:block key scoped only to the requested enabled public channel; channel creation/configuration, purchase/economic tools, elevated limits, non-public channels, and PP2 publish/live scopes remain admin-reviewed. Use this when you need protected MCP automation beyond public read/discovery tools.

  Connector

• prompt_shield

  Zambo AI Tools

  Zambo Stack — Detect prompt injection, jailbreaks, and policy bypass attempts before they reach your AI model. Two-phase analysis: instant pattern library scan (12 attack vectors) + Groq semantic analysis. Returns injection_risk 0–100, recommendation safe/review/block, and a safe rewritten version when possible. 50 free/day. Best for: 'validate user input before LLM call', 'detect jailbreak attempts', 'is this prompt safe to send to GPT?'.

  Connector

• escape_html

  IA-QA — 130+ QA & Dev Tools for AI Agents

  Escape HTML special characters (&, <, >, ", ') to their safe HTML entities. ALWAYS call this before inserting any user-provided or LLM-generated content into an HTML template to prevent cross-site scripting (XSS) attacks.

  Connector

• preflight_trust_check

  AgentLair

  Check trust readiness before engaging with an agent. Returns a ReadinessCard: trust score, behavioral maturity level, whether it's safe to engage, and any caveats. Call this before delegating tasks, accepting agent output, or authorizing payments involving an unknown agent. Free — no extra charge beyond your API key.

  Connector

• get_crime_data

  DoorProfit Crime & Neighborhood Data

  Get the crime safety score (A+ through F), crime breakdown vs national average, and recent crime incidents within 1000ft of a US address or coordinates. Use this to answer questions like "is this address/neighborhood safe?". Consumes 1 API call from the user's DoorProfit quota.

  Connector

• archive_evidence_gap

  Colour Memory

  Given a hex value and a proposed claim about it, return whether the archive supports that claim, what is missing, what kind of source would be needed, and safe agent wording. This is Colour Memory's anti-hallucination endpoint. It turns the absence of evidence into a forensic finding rather than a gap to fill with invention. Example: hex #4A535C + proposed claim 'cyanosis in a death chamber' returns: nearest archive support, support level (supported/partial/unsupported), what source type is needed, and safe wording for the agent to use. Essential for museum, documentary, editorial, legal, and forensic workflows.

  Connector