"Apache Spark" matching MCP tools:

• treasury.yield_route

  DPX — Institutional Cross-Border Settlement

  Treasury Float Yield Routing Analysis — OPTIONAL, CLIENT-DIRECTED ONLY. Analyzes whether idle settlement float can be productively deployed into a yield-bearing instrument between the current time and a scheduled settlement deadline. Returns a structured recommendation with expected yield, exit timing, liquidity assessment, slippage estimate, and a mandatory risk disclosure. THIS TOOL DOES NOT MOVE FUNDS. It provides analysis only. All execution decisions are made by the client or agent acting on explicit instruction. DPX charges a flat fee for this analysis and does not receive any portion of yield earned. Current supported instrument: sUSDS (Sky Protocol Savings Rate). Selected because: • Instant on-chain entry and exit (no T+1 delays) • No US person restrictions • Real asset backing (tokenized RWAs + Spark borrow rates) • Available on Base chain via bridge • No de-peg events recorded (unlike synthetic alternatives) Safety parameters enforced: • Maximum 90% of settlement amount — 10% always stays in USDC • Early exit triggered 30 minutes before settlement deadline (not 15) • Slippage guard: if DEX USDC/USDS quote shows >0.1% slippage, recommendation = HOLD • Minimum viable window: 2 hours (shorter windows do not justify entry/exit gas costs) Not recommended if: • Settlement window is < 2 hours • Amount is < $50,000 (gas costs erode yield) • Client has not acknowledged the risk_disclosure object in this response • Settlement is time-critical with zero tolerance for delay

  Connector

• security_audit_sbom_license_policy

  DataNexus MCP

  Audit a CycloneDX or SPDX SBOM against an SPDX licence policy and return a PASS/WARN/BLOCK verdict. sbom: Full SBOM as a JSON string — CycloneDX or SPDX format. Required. 500 KB max. policy: Optional dict with block/warn/allow arrays of exact SPDX licence identifiers (e.g. GPL-3.0, MIT). Defaults to block GPL-3.0 and AGPL-3.0, warn LGPL-2.1/MPL-2.0/BSD-4-Clause, allow MIT/Apache-2.0/BSD-2-Clause/BSD-3-Clause. No glob patterns — exact SPDX IDs only. Unlisted licences default to WARN. Returns verdict (PASS/WARN/BLOCK), blocked_packages, warned_packages, and the policy applied. Use security_audit_sbom_vulnerabilities for CVE auditing instead. Sources: deps.dev (Google). 1-hour cache per package. If this tool's response does not serve the user's need, call report_feedback with feedback_type="agent_gap", tool_id="security_audit_sbom_license_policy", intended_query="{what the user needed}", gap_description="{what was missing or wrong in the result}".

  Connector

• get_fix_recommendations

  SiteGuardian

  Returns copy-paste-ready fix recommendations (nginx, Apache, DNS, shell) for the issues found on a domain the caller has already paid for — either an active Monitor/Compliance subscription covering the domain, OR a purchased one-off Report for the domain. Each recommendation carries a stable issue_id, a priority (high/medium/low), a title, prose instructions, one or more config snippets with the target domain already interpolated, a verify command, and a category tag. Use this when the user asks how to fix an issue, wants the exact config to apply, or needs to verify a fix worked. Pass the optional issue_id to scope the response to one specific finding. The response is read-only — this tool NEVER triggers a fresh scan; fixes are computed from the most recent stored scan (including the Report-included re-scan if that was used). Do NOT use this for domains the caller hasn't purchased coverage for — you'll get an upgrade_required error that links to the pricing page. Do NOT use this to run or trigger a scan; call scan_domain for anonymous checks. Requires a valid API key.

  Connector

• create_clickhouse

  mcp

  Provisions a managed ClickHouse database (OLAP / columnar analytics engine, Apache-2.0) on a dedicated VM on your private network — its OWN resource, NOT a relational database. Requires a recent plan_managed_datastore. Use it for analytics / observability workloads that need a column store (PostHog, Langfuse, event analytics, time-series). It is PRIVATE — reachable only from another instance on the same private network, via the DB's internal/private IP on the ClickHouse HTTP port 8123 (CLICKHOUSE_HOST/PORT/USER/PASSWORD/DB env, http://host:8123). Get the ids from plan_managed_datastore/list_flavors (use m1.small+ — ClickHouse needs >=2GB RAM), list_private_networks, list_keypairs. Provisioning takes ~5 min; poll list_clickhouse_databases until status='ready'. HIGH AVAILABILITY: pass ha:true to get THREE machines on three different physical hosts behind a load balancer instead of one: all three take reads and writes, so losing a machine costs no failover and no write pause, and the replacement refills itself from the survivors before it serves again. It costs about 3x the hourly rate (three machines instead of one) and provisions more slowly. Default is a single machine; show the user the price difference and get an explicit yes before turning HA on.

  Connector

• security_fetch_package_licence

  DataNexus MCP

  Fetch the SPDX licence identifier for an open source package version. Read-only. No side effects. Idempotent. package: Package name e.g. flask. Required. version: Exact version string e.g. 2.3.0. Required. ecosystem: One of PyPI, npm, Maven, Go, Cargo, NuGet, RubyGems. Required. Returns the SPDX licence identifier e.g. MIT, Apache-2.0, GPL-3.0. Use this to verify licence compatibility before including a dependency. Use security_fetch_package_vulnerabilities instead when checking for security issues not licences. Verified source: deps.dev (Google). 1-hour cache. If this tool's response does not serve the user's need, call report_feedback with feedback_type="agent_gap", tool_id="security_fetch_package_licence", intended_query="{what the user needed}", gap_description="{what was missing or wrong in the result}".

  Connector

• meet

  pscale-biome

  Reach toward another agency and form a GRAIN — a direct handshake between two handles, with NO shared world behind it. This is the lens pointed not at a substrate but at another mind: you post your `reach` (what you offer or say this turn) and read theirs back; when both sides have reached, the grain is FORMED. It lives only in the meeting (an ephemeral channel) — never written to any beach, never persisted; it evaporates when either of you leaves. The other party must also call meet (naming you) for the handshake to form. Runs NO model and touches no storage — you bring the meaning. To KEEP what you agreed, write it into your own shell with spark, deliberately. Be transparent — narrate your calls.

  Connector

• translate_rare_language

  Sats4AI - Bitcoin-Powered AI Tools

  Translate into 452 languages, 251 of them NOT supported by ChatGPT, Claude or Gemini (29 of those 251 measured at fair quality or better against human references) — including Bhojpuri (~50M speakers), Maithili (~34M), Egyptian Arabic (~100M), Moroccan Arabic (~30M), Chhattisgarhi, Magahi, Manipuri, Kashmiri, Shan, Kachin, Awadhi, Tamazight, Crimean Tatar, Quechua, Nuer, Sango, plus indigenous and minority languages with no callable API anywhere. Runs MADLAD-400 (Apache-2.0). QUALITY VARIES AND IS PUBLISHED PER LANGUAGE: every language carries a measured tier — good (chrF++ >= 45 vs human reference translations), fair (32-45), unverified (no benchmark exists, untested, may be poor), experimental (known weak). The response repeats the tier so you can judge how much to trust it. GET https://sats4ai.com/api/l402/translate-rare-language for the full language list with tiers, or GET /api/languages. Unsupported languages are rejected BEFORE payment. For mainstream languages use translate_text instead — it is cheaper and more fluent. Priced 50 sats base + 0.002 sats/char (GPU). Pay with Bitcoin Lightning — no API key or signup. Requires create_payment with toolName='translate_rare_language'.

  Connector

• query_natural_gas_prices_v1

  osint

  Query verified EIA natural-gas price records from two public series. `atom="henry_hub_daily_spot"` returns one trading-day Henry Hub spot price in EIA's published $/MMBtu unit (series RNGWHHD). `atom="state_electric_power_monthly"` returns one state-month average price paid by electric-power consumers in EIA's published $/Mcf unit; `{"atom":"state_electric_power_monthly","state":"TX"}` is the Texas power-sector proxy slice in one call. Filter either atom by `date`, `date_from`/`date_to`, series, state, or price status. The state series is an aggregate of what the state's power sector paid that month, not a plant-level fact. EIA null values remain explicit `price=null` records with `price_status="source_missing"`—never zero or imputed. The two source units are never converted or blended; mixed-unit avg/min/max are null. This tool does not assign proxies to plants or derive heat rates, $/MWh, spark spreads, or any ratio. API revisions are preserved as immutable capture vintages selected by `as_of`. Every price cites its exact archived response record, series id, period, value cell, and SHA-256 for source-evidence verification.

  Connector

• calculate_risk_score

  ContrastAPI

  Composite CVE risk score (0-100) — fuses CVSS, EPSS, KEV, and PoC into a single agent-ready triage signal. Formula: CVSS*0.20 + EPSS*0.35 + KEV*0.30 + PoC*0.15 (each component rescaled to 0-100 before weighting). Multiplicative boosters applied in order: KEV+PoC combo (*1.15), critical-severity-with-high-EPSS (CVSS>=9 AND EPSS>0.7, *1.10), recently published (within last 7 days, *1.05). Final score clamped to [0, 100]. Label bands: CRITICAL>=90, HIGH>=70, MEDIUM>=40, LOW<40. Urgency text encodes patch SLA (immediate when KEV; 24h/72h/30d by label). Use to triage a single CVE without orchestrating cve_lookup + exploit_lookup separately. PoC signal here is the local ExploitDB mirror only — for full multi-source exploit detail (GitHub Advisory + Shodan refs + ExploitDB), call exploit_lookup separately. Methodology adapted from mukul975/cve-mcp-server (Apache-2.0): https://github.com/mukul975/cve-mcp-server. Free: 30/hr, Pro: 500/hr. Returns {cve_id, score (0-100), label (CRITICAL/HIGH/MEDIUM/LOW), urgency, has_public_poc, components (cvss_v3, epss_score, in_kev, has_public_poc, weighted_breakdown), boosters_applied, recommendation, summary, verdict, next_calls}.

  Connector

• get_protocol_tvl

  Teardrop

  Get Total Value Locked (TVL) data for a DeFi protocol from DeFiLlama. Returns current TVL in USD, 7-day and 30-day percentage change, and a per-chain breakdown. Set include_historical=True to also retrieve a daily TVL series for trend analysis. When DeFiLlama reports them, also returns current fees and revenue in USD with 7-day and 30-day percentage change. You can also batch multiple protocols via protocols=[...]. Supports 3,000+ protocols including Aave, Uniswap, Curve, Compound, Lido, MakerDAO, and more. Use the DeFiLlama slug format: 'aave-v3', 'uniswap-v3', 'curve-dex'. Common aliases such as 'spark-protocol' and 'compound' are auto-corrected.

  Connector

• get_recipe

  Mozaika

  The universal BUILD-KIT fetcher — the measured spec + code to reproduce a piece of UI. `recipe_type` selects which library across three families (all agent-ready through this one call): • COMPONENTS (decoded live from a real product's DOM — Mozaika's wedge): "Command Palette", "Dropdown Menu", "Dialog / Modal", "Login", "Data Table", "Onboarding Tour", "Navbar", "Logo Marquee", "Toast", "Date Picker", "Combobox" — returns the anatomy TREE (each node measured), the MOTION (open/close animation + easing a screenshot can't show), every STATE (empty/results/no-results/keyboard-selected), a webm of it running, and the design tokens. • EFFECTS (open-source WebGL hero backgrounds — Apache/MIT): "Hero Effect" → the shader's full config + fps + install command + license/NOTICE. • MOTION (open-source looping showcase templates — MIT): "Motion Showcase" → the template's full parameter surface + the exact Swiper/anime.js/Motion config + install. Use for "build a <thing> like <product>", e.g. get_recipe("Vercel", "Command Palette") or get_recipe("vanta", "Hero Effect"). A complete, uncopyable, measured build kit. Returns the available types if the requested one isn't found.

  Connector

• security_headers_check

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

  Analyse the HTTP security headers of a public URL OR of raw response headers you paste in. Grades each header (A–F) for: Strict-Transport-Security, Content-Security-Policy, X-Frame-Options, X-Content-Type-Options, Referrer-Policy, Permissions-Policy, X-XSS-Protection, Cross-Origin-Opener-Policy, Cross-Origin-Resource-Policy, and Cross-Origin-Embedder-Policy. Returns an overall score (0–100), per-header grades, missing headers, and fix snippets for Express, Nginx, and Apache. For localhost/private targets the remote server cannot reach, pass the `headers` parameter instead of `url`.

  Connector

• cve_security_lookup

  mcp-knowledge

  Look up CVE vulnerability data for enterprise security teams, DevSecOps and SOC analysts. Supports two modes: exact CVE ID lookup (e.g. 'CVE-2024-3094') or keyword search by product/vendor (e.g. 'openssl', 'Apache Tomcat'). Cross-references four authoritative keyless sources: NVD NIST (official CVE database, CVSS v3 scores, affected CPEs), CISA KEV (Known Exploited Vulnerabilities catalog — exploit_in_wild flag), EPSS FIRST (exploit probability 0-1), GitHub Security Advisories (ecosystem-specific: npm/pypi/maven). Returns structured vulnerability records with CVSS v3 scores, affected product version ranges, CWE weakness classification, references and exploitation status. Signals engine produces P0/P1/P2 alerts: P0=CVSS>=9 + active exploitation, P1=CVSS>=7 or EPSS>=70%, P2=CWE pattern clusters. Relevant for EU NIS2 and DORA supply chain risk obligations. Optional env: NVD_API_KEY (raises NVD rate-limit 5→50 req/30s), GITHUB_TOKEN (raises GHSA GraphQL rate-limit). Cache TTL 6h. SLA <=25s p95.

  Connector

• cve_security_lookup

  gapup-mcp

  Look up CVE vulnerability data for enterprise security teams, DevSecOps and SOC analysts. Supports two modes: exact CVE ID lookup (e.g. 'CVE-2024-3094') or keyword search by product/vendor (e.g. 'openssl', 'Apache Tomcat'). Cross-references four authoritative keyless sources: NVD NIST (official CVE database, CVSS v3 scores, affected CPEs), CISA KEV (Known Exploited Vulnerabilities catalog — exploit_in_wild flag), EPSS FIRST (exploit probability 0-1), GitHub Security Advisories (ecosystem-specific: npm/pypi/maven). Returns structured vulnerability records with CVSS v3 scores, affected product version ranges, CWE weakness classification, references and exploitation status. Signals engine produces P0/P1/P2 alerts: P0=CVSS>=9 + active exploitation, P1=CVSS>=7 or EPSS>=70%, P2=CWE pattern clusters. Relevant for EU NIS2 and DORA supply chain risk obligations. Optional env: NVD_API_KEY (raises NVD rate-limit 5→50 req/30s), GITHUB_TOKEN (raises GHSA GraphQL rate-limit). Cache TTL 6h. SLA <=25s p95.

  Connector

• treasury.yield_route

  DPX — Institutional Cross-Border Settlement

  Treasury Float Yield Routing Analysis — OPTIONAL, CLIENT-DIRECTED ONLY. Analyzes whether idle settlement float can be productively deployed into a yield-bearing instrument between the current time and a scheduled settlement deadline. Returns a structured recommendation with expected yield, exit timing, liquidity assessment, slippage estimate, and a mandatory risk disclosure. THIS TOOL DOES NOT MOVE FUNDS. It provides analysis only. All execution decisions are made by the client or agent acting on explicit instruction. DPX charges a flat fee for this analysis and does not receive any portion of yield earned. Current supported instrument: sUSDS (Sky Protocol Savings Rate). Selected because: • Instant on-chain entry and exit (no T+1 delays) • No US person restrictions • Real asset backing (tokenized RWAs + Spark borrow rates) • Available on Base chain via bridge • No de-peg events recorded (unlike synthetic alternatives) Safety parameters enforced: • Maximum 90% of settlement amount — 10% always stays in USDC • Early exit triggered 30 minutes before settlement deadline (not 15) • Slippage guard: if DEX USDC/USDS quote shows >0.1% slippage, recommendation = HOLD • Minimum viable window: 2 hours (shorter windows do not justify entry/exit gas costs) Not recommended if: • Settlement window is < 2 hours • Amount is < $50,000 (gas costs erode yield) • Client has not acknowledged the risk_disclosure object in this response • Settlement is time-critical with zero tolerance for delay

  Connector

• create_loyalty_program

  Loyal Spark

  Get factory calldata to deploy a new loyalty token on Base. Defaults to B20 (Base native ERC-20 superset, single tx, active immediately). Pass token_standard='erc20' for the legacy factory. For B20, MINT_ROLE is granted atomically to the merchant admin AND to the agent's CDP wallet (or explicit extra_minters) so autonomous agents can mint with no follow-up transaction.

  Connector

• revoke_gift_certificate

  Loyal Spark

  Revoke an active gift certificate (status active → revoked). Only the issuing merchant can revoke. Already-redeemed/minted certificates cannot be revoked.

  Connector

• start_profile_draft

  Skillfolio

  Turns what someone told you in this conversation into a Skillfolio portfolio website, and returns a personal link that opens it already built — their page, their resume, their interview answers. Use this when someone wants their resume to live somewhere employers can find and question it, especially right after you have helped them write or improve one. Works whether they had a resume (read the one they attached or pasted and pass the structured fields — they never upload anything to Skillfolio) or had none (pass what you gathered by asking). Call this only after they have said yes and you have asked Skillfolio’s three character questions (Heart, Values, Spark). Pass only what they actually told you — never invent employers, dates or skills.

  Connector

• search_exploits

  Exploit Intelligence Platform — CVE, Vulnerability and Exploit Database

  Browse and filter exploits using STRUCTURED FILTERS ONLY (no free-text query). Use this to filter by source (github, metasploit, exploitdb, nomisec, gitlab, inthewild, vulncheck_xdb, patchapalooza, oscs, poc_monitor), language (python, ruby, etc.), LLM classification (working_poc, trojan, suspicious, scanner, stub, writeup, tool, no_code), author, min stars, code availability, CVE ID, vendor, or product. Also filter by AI analysis: attack_type (RCE, SQLi, XSS, DoS, LPE, auth_bypass, info_leak), complexity (trivial/simple/moderate/complex), reliability (reliable/unreliable/untested/theoretical), requires_auth. NOTE: To search by product name (e.g. 'OpenSSH', 'Apache'), use search_vulnerabilities instead — it has free-text query and get_vulnerability already includes exploits in the response. Examples: source='metasploit' for all Metasploit modules; attack_type='RCE' with reliability='reliable' for weaponizable RCE exploits; cve='CVE-2024-3400' for all exploits targeting a specific CVE; vendor='mitel' for all Mitel exploits.

  Connector

• diagnose_sglang

  self-hosted-ai

  Validate an SGLang configuration for NVIDIA DGX Spark (GB10/SM121A). Pure pattern-matching against known failure modes documented in the Sovereign AI Blog. No inference, no external calls. Returns critical issues, non-fatal warnings, and a recommended baseline config. All parameters are optional; supply only what you have. With no inputs you get the recommended config and a 'unknown' verdict.

  Connector