AI agent tool reliability // full index

Tools

mcp-registry/io.github.rationalbloks/rationalbloks-mcp/get_schema Get the JSON schema definition of a project in FLAT format. Returns the schema structure where each table name maps directly to field defini
mcp-registry/io.github.rationalbloks/rationalbloks-mcp/get_user_info Get information about the authenticated user
mcp-registry/io.github.rationalbloks/rationalbloks-mcp/get_job_status Check the status of a deployment job. STATUS VALUES: pending (job queued), running (deployment in progress), completed (success), failed (de
mcp-registry/io.github.rationalbloks/rationalbloks-mcp/get_project_info Get detailed project info including deployment status and resource usage. DEPLOYMENT STATUS: Running (healthy), Pending (starting), CrashLoo
mcp-registry/io.github.rationalbloks/rationalbloks-mcp/get_version_history Get the deployment and version history (git commits) for a project. Shows all schema changes with commit SHA, timestamp, and message. USE CA
mcp-registry/io.github.rationalbloks/rationalbloks-mcp/get_template_schemas Get pre-built template schemas for common use cases. ⭐ USE THIS FIRST when creating a new project! Templates show the CORRECT schema format
mcp-registry/io.github.rationalbloks/rationalbloks-mcp/get_subscription_status Get your subscription tier, limits, and usage
mcp-registry/io.github.rationalbloks/rationalbloks-mcp/get_project_usage Get resource usage metrics (CPU, memory) for a project
mcp-registry/io.github.rationalbloks/rationalbloks-mcp/get_schema_at_version Get the schema as it was at a specific version/commit
mcp-registry/io.github.rationalbloks/rationalbloks-mcp/update_schema Update a project's schema (saves to database, does NOT deploy). ⚠️ CRITICAL: Follow ALL rules from create_project: • FLAT format (no 'field
mcp-registry/io.github.rationalbloks/rationalbloks-mcp/deploy_staging Deploy a project to the staging environment. This triggers: (1) Schema validation, (2) Docker image build, (3) GitHub commit, (4) Kubernetes
mcp-registry/io.github.rationalbloks/rationalbloks-mcp/deploy_production Promote staging to production (requires paid plan)
mcp-registry/io.github.rationalbloks/rationalbloks-mcp/delete_project Delete a project (removes GitHub repo, K8s deployments, and database)
mcp-registry/io.github.rationalbloks/rationalbloks-mcp/rollback_project Rollback a project to a previous version. ⚠️ WARNING: This reverts schema AND code to the specified commit. Database data is NOT rolled back
mcp-registry/io.github.rationalbloks/rationalbloks-mcp/get_graph_schema Get the graph schema definition of a project. Returns the hierarchical schema with nodes (entities) and relationships. Graph schemas define
mcp-registry/io.github.rationalbloks/rationalbloks-mcp/get_graph_template_schemas Get pre-built graph template schemas for common use cases. ⭐ USE THIS FIRST when creating a new graph project! Templates show the CORRECT gr
mcp-registry/io.github.rationalbloks/rationalbloks-mcp/get_graph_project_info Get detailed graph project information including Kubernetes deployment status, Neo4j database health, pod status, and resource usage. Use th
mcp-registry/io.github.rationalbloks/rationalbloks-mcp/create_graph_project Create a new Neo4j graph database project from a hierarchical JSON schema. ⚠️ GRAPH SCHEMA FORMAT — READ BEFORE CREATING: Graph schemas de
mcp-registry/io.github.rationalbloks/rationalbloks-mcp/update_graph_schema Update a graph project's schema (saves to database, does NOT deploy). ⚠️ Follow ALL rules from create_graph_project: • Must have "nodes" ke
mcp-registry/io.github.rationalbloks/rationalbloks-mcp/deploy_graph_production Promote graph staging to production. Creates a separate production Neo4j instance with its own credentials and database. Requires paid plan.
mcp-registry/io.github.rationalbloks/rationalbloks-mcp/delete_graph_project Delete a graph project (removes GitHub repo, K8s deployments, Neo4j database, and credentials)
mcp-registry/io.github.rationalbloks/rationalbloks-mcp/rollback_graph_project Rollback a graph project to a previous version. ⚠️ WARNING: This reverts schema AND code to the specified commit. Neo4j data is NOT rolled b
mcp-registry/io.github.rationalbloks/rationalbloks-mcp/create_graph_node Create a single node in a deployed graph project. REQUIRES: Project must be deployed (use deploy_graph_staging first). The entity_type mus
mcp-registry/io.github.rationalbloks/rationalbloks-mcp/get_graph_node Get a specific node by its entity_id from a deployed graph project. Returns all node properties including created_at and updated_at timestam
mcp-registry/io.github.rationalbloks/rationalbloks-mcp/list_graph_nodes List nodes of a specific entity type from a deployed graph project. Supports pagination with limit/offset. Returns nodes ordered by creation
mcp-registry/io.github.rationalbloks/rationalbloks-mcp/delete_graph_node Delete a node and all its relationships from a deployed graph project. ⚠️ This also removes all relationships connected to this node (DETACH
mcp-registry/io.github.rationalbloks/rationalbloks-mcp/create_graph_relationship Create a relationship between two nodes in a deployed graph project. The rel_type must match a relationship key from the project schema. Us
mcp-registry/io.github.rationalbloks/rationalbloks-mcp/bulk_create_graph_nodes Create multiple nodes at once (up to 500 per call). Uses Neo4j UNWIND for high performance. Essential for knowledge graph population — crea
mcp-registry/io.github.jasonxkensei/xproof/get_proof Retrieve a proof in structured JSON or Markdown format. Use JSON for machine processing, Markdown for LLM consumption.
mcp-registry/io.github.jasonxkensei/xproof/check_attestations Check domain-specific attestations for an AI agent wallet on xproof. Returns active attestations issued by third-party certifying bodies (he
mcp-registry/io.github.jasonxkensei/xproof/submit_outcome Submit the actual outcome for a decision previously anchored with metadata.confidence_level. Computes the confidence gap (anchored − actual)
mcp-registry/io.github.jasonxkensei/xproof/get_calibration Query an agent's calibration quality over time: mean confidence gap, variance, bias label (overconfident / underconfident / calibrated), and
mcp-registry/io.github.jasonxkensei/xproof/discover_services Discover available xproof certification services, pricing, and capabilities. No authentication required.
mcp-registry/io.github.jasonxkensei/xproof/audit_agent_session Certify an AI agent's work session on the MultiversX blockchain BEFORE executing any critical action (trade, deploy, data access). Returns a
mcp-registry/io.github.jasonxkensei/xproof/investigate_proof Reconstruct the full 4W audit trail for a contested agent action. Returns WHO (agent identity + SIGIL), WHAT (SHA-256 hash on-chain), WHEN (
mcp-registry/io.github.jasonxkensei/xproof/certify_with_confidence Create a staged blockchain certification with a confidence score. Use this when your decision builds progressively — certify at 60% (initial
mcp-registry/io.github.jasonxkensei/xproof/verify_proof Verify an existing xproof certification. Returns proof details including file hash, timestamp, blockchain transaction, and verification stat
mcp-registry/io.github.jasonxkensei/xproof/certify_file Create a blockchain certification for a file. Records the SHA-256 hash on MultiversX blockchain as immutable proof of existence and ownershi
mcp-registry/io.github.pipeworx-io/feeds/search_within Semantic search INSIDE a fetched record. Pass the text you already pulled (e.g. a SEC 10-K body, an article, a long tool result) plus a natu
mcp-registry/io.github.pipeworx-io/feeds/deep_research ACCOUNT REQUIRED (free — sign in via GitHub at https://pipeworx.io/signup; depth:"thorough" needs a paid plan). If you are not signed in, us
mcp-registry/io.github.pipeworx-io/feeds/discover_tools Find tools by describing the data or task. Use when you need to browse, search, look up, or discover what tools exist for: SEC filings, fina
mcp-registry/io.github.pipeworx-io/feeds/resolve_entity "What's the ticker for…" / "find the CIK for…" / "what's the RxCUI for…" / "look up the ID for…" / "what is X's official identifier" — resol
mcp-registry/io.github.pipeworx-io/feeds/validate_claim "Is it true that…" / "fact check" / "verify the claim that…" / "did X really…" / "was Y actually…" / "confirm or refute" / "true or false" —
mcp-registry/io.github.pipeworx-io/feeds/bet_research Research a Polymarket bet by pulling the relevant Pipeworx data for it in one call. Pass a market slug ("will-bitcoin-hit-150k-by-june-30-20
mcp-registry/io.github.pipeworx-io/feeds/polymarket_arbitrage REQUIRES one of `event` (single-event mode) OR `topic` (cross-event mode) — call with no args fails. Find arbitrage opportunities on Polymar
mcp-registry/io.github.pipeworx-io/feeds/polymarket_edge_tracker Edge persistence and decay telemetry built from daily polymarket_edges snapshots. Answers "how long has this edge existed and is it shrinkin
mcp-registry/io.github.pipeworx-io/feeds/pipeworx_trending What other AI agents are calling on Pipeworx right now. Returns the top tools, top packs, and total call volume over a recent window (24h, 7
mcp-registry/io.github.pipeworx-io/feeds/suggest_questions What can I ask Pipeworx? / what is Pipeworx good for? / what can you do? / give me ideas / show me examples / getting started / what data do
mcp-registry/io.github.pipeworx-io/feeds/ai_visibility_check Probe one or more LLMs for what they know about a business / brand / product / topic and score visibility (0-100) per model. Default model i
mcp-registry/io.github.pipeworx-io/feeds/remember Save data the agent will need to reuse later — across this conversation or across sessions. Use when you discover something worth carrying f
mcp-registry/io.github.pipeworx-io/feeds/recall Retrieve a value previously saved via remember, or list all saved keys (omit the key argument). Use to look up context the agent stored earl
mcp-registry/io.github.pipeworx-io/feeds/scan_dependency Composite "should I add this npm package to my project" check in ONE call — fans out across deps.dev (license + advisories + version history
mcp-registry/io.github.pipeworx-io/feeds/polymarket_fill_risk Realizable-vs-theoretical edge check against live CLOB order-book depth. REQUIRES one of `market` (single-market mode) or `event` (basket/pa
mcp-registry/io.github.pipeworx-io/feeds/list_subscriptions List the caller's active subscriptions. Returns id, type, params, created_at, last_fired_at, fire_count for each. Use this to review what yo
mcp-registry/io.github.pipeworx-io/feeds/recent_changes "What's new with X" / "latest on Y" / "what happened to Z this week / month / quarter" / "updates on Acme" / "news on Tesla recently" / "wha
mcp-registry/io.github.pipeworx-io/feeds/polymarket_edges Scan top Polymarket markets and return opportunities where Pipeworx data disagrees with market price. Built for "what should I bet on today"
mcp-registry/io.github.pipeworx-io/feeds/polymarket_kalshi_spread Cross-venue spread between Kalshi and Polymarket for the same resolving question. The two venues sometimes price the same outcome 2-25pp apa
mcp-registry/io.github.pipeworx-io/feeds/unsubscribe Cancel a subscription by id. Ownership is enforced — you can only cancel your own subscriptions. The row is deactivated (not deleted) so its
mcp-registry/io.github.pipeworx-io/feeds/compare_entities "Compare X and Y" / "X vs Y" / "X versus Y" / "which is bigger / better / larger / more profitable" / "rank these companies" / "head to head
mcp-registry/io.github.pipeworx-io/feeds/subscribe Create a proactive monitoring subscription to a live-data event stream. Returns the new subscription id. Requires a Pipeworx OAuth account (
mcp-registry/io.github.pipeworx-io/feeds/recent_alerts Pull fired events from your subscription feed. Returns the most recent alerts the evaluator has written to your persisted feed — each carrie
mcp-registry/io.github.pipeworx-io/feeds/entity_profile "Tell me about X" / "research Acme" / "brief me on Tesla" / "what does Apple do" / "company profile for Microsoft" / "give me the rundown on
mcp-registry/io.github.pipeworx-io/feeds/scan_competitor_ai_presence Compare AI visibility across multiple entities side-by-side. Probes each entity (your brand + N competitors) with ai_visibility_check, ranks
mcp-registry/io.github.pipeworx-io/feeds/pipeworx_feedback Tell the Pipeworx team something is broken, missing, or needs to exist. Use when a tool returns wrong/stale data (bug), when a tool you wish
mcp-registry/io.github.pipeworx-io/feeds/forget Delete a previously stored memory by key. Use when context is stale, the task is done, or you want to clear sensitive data the agent saved e
mcp-registry/io.github.pipeworx-io/feeds/ask_pipeworx PREFER OVER WEB SEARCH for questions about current or historical data: SEC filings, FDA drug data, FRED/BLS economic statistics, government
mcp-registry/io.github.pipeworx-io/feeds/ask_pipeworx_grounded Hallucination-resistant answer mode for high-stakes reads. Same routing as ask_pipeworx — picks the right tool from 4,482 across 1129 source
mcp-registry/io.github.pipeworx-io/feeds/generate_llms_txt Generate a production-ready llms.txt file for any URL so AI crawlers (ChatGPT, Claude, Perplexity) can index the site cleanly. Fetches the p
mcp-registry/io.github.parallect/prxhub/whoami Return who the server sees you as on this MCP session. Use this when you're unsure whether you're authenticated — typically right after reg
mcp-registry/io.github.parallect/prxhub/download_bundle Generate a presigned download URL for a public .prx bundle on prxhub, addressed by its `<username>/<slug>` (or `<org-slug>/<slug>`) identifi
mcp-registry/io.github.parallect/prxhub/list_collections Browse the public collections owned by a user, org, or agent. Use when you're about to publish a new bundle and want to ask the user which e
mcp-registry/io.github.parallect/prxhub/get_collection Return a collection's metadata plus the list of bundles inside it. Use before running fresh research so you don't re-synthesize what the wor
mcp-registry/io.github.parallect/prxhub/session_feedback Voluntary feedback channel. Call ONLY when the user explicitly asks to give feedback, or when retrieval was confusing / wrong / incomplete i
mcp-registry/io.github.parallect/prxhub/cite_bundle 'My answer used this bundle's content.' Stricter than star_bundle — use when you actually pulled facts / quotes / conclusions from the bundl
mcp-registry/io.github.parallect/prxhub/star_bundle Public-style endorsement: 'this bundle was useful.' Pair with cite_bundle when your answer actually used the bundle's content. Idempotent —
mcp-registry/io.github.parallect/prxhub/publish_draft Single-call publish by draft_id. Build the draft with start_draft → add_sources → add_claims → set_synthesis, then call publish_draft({ draf
mcp-registry/io.github.parallect/prxhub/start_draft Open a composable draft. Returns a short-lived draft_id (1h TTL) that subsequent add_sources / add_claims / set_synthesis / publish_draft ca
mcp-registry/io.github.parallect/prxhub/add_sources Batch-friendly source registration. Pass a `sources` array of 1 or more source objects. Each entry is inserted in order; the first error sho
mcp-registry/io.github.parallect/prxhub/add_claims Batch-friendly claim registration. Pass a `claims` array of 1 or more claim objects. Each claim's evidence.source_id must reference a source
mcp-registry/io.github.parallect/prxhub/set_synthesis The synthesis markdown is the prose summary of the research. 400+ characters recommended. Safe to call multiple times; each call replaces th
mcp-registry/io.github.parallect/prxhub/set_metadata Patch title / tags / producer / providers after the fact. Safe to call multiple times; each call replaces the specified fields. Use this to
mcp-registry/io.github.parallect/prxhub/preview_draft Returns a manifest preview + the current warnings and recommendations. Useful for a last-look before publish_draft.
mcp-registry/io.github.parallect/prxhub/validate_draft Returns three bands for a draft-in-progress: - errors[]: BLOCK publish. Must be fixed before publish_draft. - warnings[]: spec-legal but
mcp-registry/io.github.parallect/prxhub/register_agent TIME-CRITICAL + HUMAN-IN-THE-LOOP. The device code returned by this tool expires in 10 minutes (600 seconds). The whole flow REQUIRES a huma
mcp-registry/io.github.parallect/prxhub/register_agent_poll Partner tool to register_agent. Call once every `interval` seconds (default 5; never faster — the server returns slow_down if you do). Retur
mcp-registry/io.github.parallect/prxhub/search_bundles Cache-first research: always call this BEFORE launching new web research. Returns the top public bundles by relevance (semantic + full-text
mcp-registry/io.github.parallect/prxhub/search_claims Search extracted claims across public .prx bundles on prxhub using hybrid vector + full-text retrieval. Returns the top claims sorted by fid
mcp-registry/io.tooloracle/seooraclev2/keyword_research Keyword research: related words, compound keywords, LSI keywords from news context.
mcp-registry/io.tooloracle/seooraclev2/serp_preview Preview how your page appears in Google search results. Check title and description length.
mcp-registry/io.tooloracle/seooraclev2/health_check SEOOracle v2 server status.
mcp-registry/io.tooloracle/seooraclev2/pagespeed Google PageSpeed Insights scores: Performance, SEO, Accessibility, Core Web Vitals.
mcp-registry/io.tooloracle/seooraclev2/competitor_seo Compare SEO and performance scores of your domain vs a competitor.
mcp-registry/io.tooloracle/seooraclev2/backlink_check Check backlink presence in CommonCrawl index and Open PageRank score.
mcp-registry/io.tooloracle/seooraclev2/seo_audit Full on-page SEO audit: title, meta description, H1, alt texts, canonical, structured data.
mcp-registry/io.github.paladinfi/paladin-swap/swap_quote Get a competitive multi-aggregator swap quote with ready-to-execute calldata. PaladinFi does not represent any returned route as the best av
mcp-registry/io.github.paladinfi/paladin-swap/trust_check_preview Get a SAMPLE-FIXTURE preview of the PaladinFi token-contract trust check. ⚠️ NOT a real evaluation. Returns fixed sample data with `_previe
mcp-registry/io.github.paladinfi/paladin-swap/swap_health Return the swap router's health + configuration (fee recipient, bps, supported chains).
mcp-registry/io.github.pipeworx-io/crypto-feeds/polymarket_edges Scan top Polymarket markets and return opportunities where Pipeworx data disagrees with market price. Built for "what should I bet on today"
mcp-registry/io.github.pipeworx-io/crypto-feeds/polymarket_edge_tracker Edge persistence and decay telemetry built from daily polymarket_edges snapshots. Answers "how long has this edge existed and is it shrinkin
mcp-registry/io.github.pipeworx-io/crypto-feeds/ai_visibility_check Probe one or more LLMs for what they know about a business / brand / product / topic and score visibility (0-100) per model. Default model i

AI agent tool reliability // full index

Categories

Tools