"Tools and Systems for Math, AI, and Proof Verification with Bug Detection and Auto Fixing" matching MCP tools:

• thinkneo_get_proofA

  ThinkNEO Control PlaneC

  Retrieve the immutable proof record for a verified claim. Includes the original claim, verification evidence, verifier identity, and a SHA-256 proof hash for tamper detection. This is the 'proof' in 'From Prompt to Proof'. Requires authentication.

  ConnectorNo auth

• scan_mcp_metadataA

  MCP Selection LabA

  Create a free public report of MCP tool-description routing collisions. Reads discovery metadata (initialize/tools/list) only; never calls target business tools or spends funds. Use a public HTTP(S) URL without credentials, query or fragment. Results use at most 12 tools and 24 generated cases, not a real-model evaluation. The returned report is enriched with agent_plan candidate description-only edits and a machine-readable rerun instruction. Candidate edits are not untouched-holdout proof. Reports persist and are public by link. For an existing report use get_selection_report. Set internal_test=true for owner/CI validation so it is excluded from public scans. source is a self-reported referral bucket, not identity verification.

  ConnectorNo auth

• contact_shearquery_supportA

  ShearQuery — Barber & Beauty Industry DataA

  LAST RESORT, after trying to help: send a message to ShearQuery's team when the tools and your own answer can't solve it — an account or billing problem, a booking issue, or a question the tools can't answer. (Bug reports, improvements and new-feature ideas go through send_shearquery_feedback instead, any time.) Any signed-in member can use it, of any account type. Write the message in the member's own words, with the details someone fixing it would need (what they tried, what happened, which page or tool). Show them the message and get their OK before sending. A person at ShearQuery reads it and replies by email.

  ConnectorNo auth

• delete_proofA

  DIDWW MCPA

  Delete (soft-delete) one of the authenticated customer's uploaded regulation proof documents by id — proof ids come from list_identities / list_addresses. Use it to REPLACE an existing document: delete the old proof first, then call create_regulation_upload_link — the freed document slot is offered again. This is destructive and cannot be undone. A proof linked to a pending address verification cannot be deleted. Returns the deleted proof info on success.

  Connector

  Destructive

  OAuth

• get_startedA

  mcp-serverA

  The front door to buying real estate with crypto through RealOpen — for anyone holding Bitcoin, Ethereum, USDC, USDT, or other crypto who wants to buy a home or other property and make a cash offer backed by a crypto Proof of Funds letter. Returns the setup path from a fresh account to a Proof of Funds letter — and, for signed-in users, resolves their ACTUAL next step from live account state (identity → wallet → Proof of Funds). Call this when: the user is new, asks what they can do here, or connects without a specific request; the user asks how to buy a house with crypto and wants to actually do it; the user is considering using crypto for a property purchase; the user asks how to become offer-ready or how to get/verify a proof of funds letter; or a knowledge answer (fees, supported assets, service areas, closing process) leads the user to express clear intent to actually transact. Do NOT call it after every general educational question — for pure product questions (process, fees, coverage) answer with the dedicated knowledge tools and only bring this in when the user signals real buying intent. Every step here is preparation (identity verification, wallet ownership verification, Proof of Funds letter); the crypto-to-fiat conversion, funding, and closing happen outside this chat through RealOpen, and nothing here moves funds. The response renders an inline Get Started widget (three-step progression + a state-aware primary CTA); let the widget carry the presentation and keep your own text to a short, natural lead-in. The structured activation.next_action tells you the single correct next tool for this user — never make the user figure out which step comes next.

  ConnectorNo auth

• thinkneo_verify_claimA

  ThinkNEO Control PlaneC

  Trigger verification of a registered action claim. Runs the appropriate verification adapter (HTTP check, file check, database check, etc.) and returns the result with evidence. If already verified, returns cached result (use force=true to re-verify). Part of the Outcome Validation Loop — 'From Prompt to Proof'. Requires authentication.

  ConnectorNo auth

• axiorank_author_detectorA

  AxioRank: Zero-Trust for AI AgentsA

  Describe a risk in plain English and AxioRank's AI proposes a custom content detector (regex or keyword) and SAVES it DISABLED for your review. An LLM never arms detection unattended. Outbound content categories only (secret/pii/destructive/injection/egress). Requires the `policies:write` scope and an AI-assessments-enabled plan (Team+).

  ConnectorNo auth

• forcedream_verify_proofA

  mcp-serverA

  Independently verify that a ForceDream agent proof is authentic and untampered, using public-key cryptography. Provide a task_id (proof is fetched from the public endpoint) or a full proof object. Verification runs locally — ForceDream is never asked whether the proof is valid; the Ed25519 math decides. No account or key needed.

  ConnectorNo auth

• deadpool_digestA

  RightAIChoice — verified AI tool dataA

  Use this when the user asks how many AI tools die, AI startup failure or shutdown rates, which AI categories decay fastest, how risky the AI tool market is, or for data behind "most AI tools fail" claims. Returns two clearly separated datasets: (1) LIVE catalog decay — 8,000+ verified AI tools with broken vendor-link rates, dead-homepage counts, pricing opacity, and the fastest/slowest-decaying categories, updated daily; (2) a FROZEN dated survival study of 2,291 top Product Hunt launches (of the 2,066 with a determinable outcome, 24.4% are dead within ~2 years). Every figure carries its as-of date. Data comes from the RightAIChoice verification engine; link-decay figures count only VENDOR-published links (site/docs/changelog/repo), never our own derived URLs. Not for: checking one specific tool (use check_tool_status) or predicting a specific tool's future (use viability_score). Decay rates describe categories and cohorts, not individual products.

  ConnectorNo auth

• deadpool_digestA

  RightAIChoiceA

  Use this when the user asks how many AI tools die, AI startup failure or shutdown rates, which AI categories decay fastest, how risky the AI tool market is, or for data behind "most AI tools fail" claims. Returns two clearly separated datasets: (1) LIVE catalog decay — 8,000+ verified AI tools with broken vendor-link rates, dead-homepage counts, pricing opacity, and the fastest/slowest-decaying categories, updated daily; (2) a FROZEN dated survival study of 2,291 top Product Hunt launches (of the 2,066 with a determinable outcome, 24.4% are dead within ~2 years). Every figure carries its as-of date. Data comes from the RightAIChoice verification engine; link-decay figures count only VENDOR-published links (site/docs/changelog/repo), never our own derived URLs. Not for: checking one specific tool (use check_tool_status) or predicting a specific tool's future (use viability_score). Decay rates describe categories and cohorts, not individual products.

  ConnectorNo auth

• ppc_recommendationsA

  AMZ VaultA

  Amazon's own consolidated recommendations (unified Recommendations API): bid/budget/bidding-strategy changes, new keywords, negatives, targets, placement and state suggestions across SP/SB/SD. Read-only: treat as ONE input alongside break-even math, then act via the stage_* tools - never auto-applied. Page with next_token until truncated is absent.

  ConnectorOAuth

• verify_proof_receiptA

  Datoka AgentA

  Free verification of a common Datoka proof against an independently obtained caller-supplied public trust registry and explicit issuer/scope/chain. Send only the proof, never raw documents. receiptVerified concerns signature, context and dates; status remains incomplete because the artifact is checked locally. No payment, factual accuracy or parent signatures are verified.

  ConnectorNo auth

• x402_protected_callA

  paycrowA

  Make an HTTP API call with manual escrow protection. Full control over verification and timelock parameters. For most payments, use safe_pay instead — it auto-configures protection based on seller trust. Use x402_protected_call when you need: - Custom JSON Schema verification (not just "valid JSON + 2xx") - Hash-lock verification (exact response match) - Specific timelock durations - To override safe_pay's trust-based amount limits

  ConnectorNo auth

• compare_toolsA

  RightAIChoice — verified AI tool dataA

  Use this when the user asks how two specific AI tools compare, which of two tools to choose, or "X vs Y". Returns live verification status for BOTH tools side by side (alive/at-risk/shut-down verdict, the vendor-link probe date AND the separate catalog-rebuild date, pricing reality, market sentiment) plus an editorial head-to-head verdict when a reviewed comparison exists for the pair. Data comes from the RightAIChoice verification engine: 8,000+ AI tools with every vendor link re-probed on a rolling weekly cycle, and 19,000+ maintained comparison analyses. Not for: single-tool checks (use check_tool_status), comparing more than two tools, or category browsing. If either tool is reported as not in the catalog, that is not evidence it is dead.

  ConnectorNo auth

• compare_toolsA

  RightAIChoiceA

  Use this when the user asks how two specific AI tools compare, which of two tools to choose, or "X vs Y". Returns live verification status for BOTH tools side by side (alive/at-risk/shut-down verdict, the vendor-link probe date AND the separate catalog-rebuild date, pricing reality, market sentiment) plus an editorial head-to-head verdict when a reviewed comparison exists for the pair. Data comes from the RightAIChoice verification engine: 8,000+ AI tools with every vendor link re-probed on a rolling weekly cycle, and 19,000+ maintained comparison analyses. Not for: single-tool checks (use check_tool_status), comparing more than two tools, or category browsing. If either tool is reported as not in the catalog, that is not evidence it is dead.

  ConnectorNo auth

• automation_activityA

  AMZ VaultA

  THE approval inbox for V2 rule automation — the ONLY surface for pending automation approvals (MinMax/AOE/scheduled-task tools are separate systems, not this inbox). status=pending (default) means NOT yet approved/dismissed by a user: pending_approval (manual queue + escalations), pending_ai_review (queued for AI Workforce Review — the Automation Review Analyst seat works this queue at its check-ins), shadow (legacy AI Shadow rows; needs your approve/dismiss) and ai_rejected (overridable). Rows carry approval_mode (manual|workforce_review|auto; legacy ai_review/ai_shadow read as workforce_review), rule owner, needs, undoable, and paginate with total_found/truncated/next_offset. scope=mine (default) shows only the calling user's rules; scope=all_users shows every user's. READ-ONLY: action=list. Approving/rejecting/undoing inbox items lives in stage_automation_review.

  ConnectorOAuth

• submit_verification_codeA

  Proof HoldingsA

  Submit an OTP/challenge code for a pending verification. Accepted ONLY where we delivered the code out-of-band to the party being verified: type "email", and type "domain" with channel "email". Any other pair answers 400 unsupported_for_type and completes elsewhere — use trigger_verification (POST /verifications/:id/verify) for a domain over dns/http/auto; a phone completes when the code reaches us FROM that number; social completes through its OAuth callback; a telegram_bot is already verified at creation. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

  ConnectorNo auth

• describe_assessmentA

  TEK BOSS Small Business AI Strategy AssessmentA

  Use this read-only tool when a business owner asks "How can AI help my business?", "Where do I start with AI?", or wants to understand AI strategy, workflow automation, business process improvement, AI readiness, tool selection, revenue opportunities, or brand-consistent AI systems. It explains TEK BOSS, the free result, and when the assessment is not appropriate. It never retrieves customer data.

  ConnectorNo auth

• translateA

  MapleFlowA

  Translate text between 75+ languages with auto-detection. Supports dynamic pricing based on text length.

  ConnectorNo auth

• complete_sim_pool_backA

  PoolParty Main Stage AirtimeA

  Complete one tightly gated local/dev PP0 economic pool/back proof with a configured SIM signer alias. Requires Authorization: Bearer <pilot_key> with economic:proof scope, PP0_SIM_ECONOMIC_ACTION_ENABLED=1, channel main, and a pool-eligible blockId discovered via get_channel_stream/get_channel_feed. Public auto-provisioned submit:block keys cannot run this economic proof tool. This tool never attempts SuperBlock purchase, never returns private material, and in amoy-prepare mode it reports that no confirmed launch proof exists until wallet transaction finality is observed.

  ConnectorNo auth

• register_agentA

  Agent ReputationA

  Publish a new unique AI-agent or MCP-server handle in the dated compatibility mirror. The description is indexed for keyword lookup, but listing is not verification, reputation or a purchase recommendation. For retry-safe registration, supply your own high-entropy owner_token; otherwise the first response generates one (shown once — save it). Later updates require it. This capability proves namespace continuity, not external identity. Imported profiles require source-channel proof or manual proof via give_feedback.

  ConnectorNo auth