"Tools for Comparing Code Changes and Identifying Potential Bugs" matching MCP tools:

• leave_feedbackA

  AgentMarketplaceA

  Leave feedback about AgentMarketplace itself — bugs, confusing tools, feature requests. This is for feedback about the platform, not about a counterparty. There is no reputation or rating system here — that lives in AgentTrust. Args: access_token: AgentAuth bearer token (requires ``market.read``). message: Free-text feedback, up to 2000 characters. Returns: ``{"recorded": true}`` on success.

  ConnectorNo auth

• ask_agentA

  SwogeAgenticA

  Use this when a question needs several of these tools chained together and a written answer, for example comparing tokens or researching a launcher. SwogeAgentic, a Claude agent, picks the tools, reads the numbers and answers in Markdown with its sources and sample sizes. API key only: billed at its real cost, up to the quoted maximum ("quote": true gives it). Takes 10 to 60 seconds.

  ConnectorNo auth

• create_support_ticketA

  BorealHostB

  Open a support ticket with the BorealHost team. Use this to escalate platform-side problems you cannot fix with the available tools (billing issues, infrastructure faults, API bugs). A human answers every ticket — poll get_support_ticket for updates. Requires: API key with write scope. Args: subject: Short summary (max 200 chars) message: Full description (max 20000 chars) category: Optional (e.g. "technical", "billing") site: Optional site slug the ticket concerns Returns: {"id", "subject", "status", "message": "Ticket created..."}

  ConnectorNo auth

• ado_query_workitemsA

  ALM X++ MCP ServerA

  AZURE DEVOPS ONLY -- Query Work Items (Bugs, Tasks, FDDs, User Stories, CRs) in Azure DevOps. [~] PRIORITY TRIGGER: use this tool when the user mentions 'FDD', 'RDD', 'IDD', 'CR', 'Task', 'Workitem', 'Work Item', 'Bug', 'User Story', 'Feature', 'Issue', 'ticket', 'sprint', 'backlog', 'DevOps', 'liste des tâches', 'show tasks', 'find bugs', '#1234', 'WI#'. NEVER use this tool for: D365 labels (@SYS/@TRX), X++ code, AOT objects, tables, classes, forms, enums, error messages, 'c\'est quoi le label', 'search_labels', 'libellé', 'label D365'. For labels -> use search_labels. For D365 code -> use search_d365_code or get_object_details. Shortcuts: 'bugs' (all active bugs), 'my bugs' (assigned to me), 'recent' (updated last 7 days), 'sprint' (current iteration). Or pass any WIQL SELECT statement or a free-text title search. Use '*' with filters only. Returns max 50 work items with ID, title, type, state, priority, area, assigned-to. Requires DEVOPS_ORG_URL + DEVOPS_PAT env vars.

  ConnectorNo auth

• check_injectionA

  ContrastAPIA

  Scan source code for injection vulnerabilities: SQL injection, command injection, path traversal via unsafe string concatenation/unsanitized input. Supports Python, JavaScript, TypeScript, Java, Go, Ruby, Shell, Bash. Use to detect input-handling bugs; for secrets use check_secrets. Companion code-security tools: check_secrets (hard-coded credential detection), check_dependencies (known-CVE vulnerability audit), check_headers (live HTTP security-header validation), scan_headers (live HTTP scan via domain). Free: 30/hr, Pro: 500/hr. Returns {total, by_severity, findings}. No data stored.

  ConnectorNo auth

• post_lint_javascriptA

  webbersites-x402-data-apiA

  JavaScript / Node lint: POST {code}, get the bugs back with line numbers. Syntax errors come from the real V8 parser (compile-only — code is never executed), plus deterministic checks: loose == coercion, assignment in conditions, comparisons with NaN, const reassignment (runtime TypeError), var pitfalls, unused variables, leftover console.log. Handles ESM imports, template literals, regex. No AI. Max 128 KB. ($0.002 per call, paid via x402)

  ConnectorNo auth

• list_psr_typesA

  entsoe-mcpA

  List production-type (psr_type) codes. Pass zone= to scope the answer. Most codes are ENTSO-E's B01..B25 and mean the same thing in every ENTSO-E zone. A few are source-native (source != "entsoe") and exist only where that source publishes — they express concepts the B-codes cannot, so they are NOT interchangeable with a similar-looking B-code. Check `source` and read `description` before comparing a code across zones. Passing zone= also returns `taxonomy_note` for zones that mix taxonomies (e.g. GB), and per-code `endpoints` showing where each code comes from. Each code carries `counts_as_generation`: when False the figure is a net flow or net storage number, not production — do not sum it into a generation total.

  ConnectorNo auth

• seo_generate_code_fixA

  mcp-seoA

  Generates framework-aware code fixes (Laravel Blade, Next.js App/Pages Router, HTML, PHP, Astro, Svelte) for missing titles, meta descriptions, canonical URLs, JSON-LD schemas, and WebMCP discovery links with unified diff preview. USAGE GUIDELINES: - Use after audit tools detect specific SEO, schema, or WebMCP issues in a source file. - Do NOT use for general code refactoring unrelated to metadata, schema, or SEO tags. - Always run 'seo_validate_code_fix' immediately after applying changes to verify syntax and prevent duplicate tags. BEHAVIORAL TRANSPARENCY: - Non-destructive by default: Returns unified diff preview without modifying files. - Modifies disk ONLY when 'applyDirectly' is explicitly set to true.

  ConnectorNo auth

• event_redeem_codeA

  Sonar ConnectionsA

  Seats the person at an event with an event code from a badge, a poster, an email or a door. Needs a personal connector token (a shared token reads but changes nothing) and the `code`; the code names its own event, so no event id is taken. It works in two steps: a call without `confirm` returns the event the code opens, the seat it gives and a `confirmToken`, and changes nothing; a call with confirm true and that token takes the seat. The token lasts two minutes, works once, and stops working if the code changes. Redeeming works from anywhere, not only at the venue.

  ConnectorNo auth

• workmine_catalogA

  WORKMINEA

  Browse the complete WORKMINE catalog for free: paid API names, exact USDC-denominated prices, HTTP methods and URLs. Use this when comparing available tools; use find_workmine_tool when you already have a natural-language task. This catalog call itself does not execute or purchase a paid API.

  ConnectorNo auth

• publishA

  StayCharted AMTA

  Make a trained version the live one, used by fills, classify and the Prediction API. Two steps: the first call changes nothing and returns what will change plus a confirmation code; show that to the user, and only after they explicitly agree call again with that exact code. The user's yes is not the code. A code works once, for this model and these arguments, for 10 minutes.

  Connector

  Destructive

  OAuth

• quality_qr_updateA

  Quality QRA

  Update an existing QR code's properties. Use this when the user wants to change where a QR code points to, rename it, or enable/disable it. Destination URL changes only work for dynamic URL-based types (url, pdf, menu, app-store, social). Name and active status can be changed for any QR code type.

  ConnectorNo auth

• get_tract_sviA

  CDC Social Vulnerability IndexA

  Get tract-level CDC Social Vulnerability Index data within a county. Returns overall SVI and all four theme percentile rankings for each census tract in the specified county. Useful for identifying sub-county areas of high vulnerability. Args: state: Two-letter US state abbreviation (e.g. 'WA', 'CA'). county_fips: 5-digit county FIPS code (e.g. '53033' for King County, WA). year: SVI data year (default 2022, currently only 2022 available). limit: Maximum number of tracts to return (default 50, max 500).

  ConnectorNo auth

• get_food_environmentA

  USDA Food AccessA

  Get county-level food access risk profiles using Census ACS data. Constructs food access risk profiles by combining vehicle access (B25044), poverty status (B17001), and SNAP participation (B22001). Limited vehicle access combined with high poverty indicates food desert risk. Useful for identifying areas with barriers to food access in grant applications. Args: state: Two-letter state abbreviation (e.g. 'WA', 'MS') or 2-digit FIPS code. county_fips: Three-digit county FIPS code (e.g. '033' for King County, WA). Omit to get all counties in the state.

  ConnectorNo auth

• post_lint_phpA

  webbersites-x402-data-apiA

  PHP lint: POST {code}, get the bugs back with line numbers. Deterministic static analysis — code is never executed, no AI. Catches SQL injection (request data interpolated into query strings), the removed mysql_* API, unbalanced braces, '+' string concat, = vs == in conditions, type-juggling loose comparisons, eval/extract on request data, unused variables, leftover var_dump. Understands PHP tags, heredocs, interpolation. Max 128 KB. ($0.002 per call, paid via x402)

  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

• flow_whale_contextA

  f1owA

  Aggregate whale context for one coin (cohort-level, no individual wallets): per-exchange reserve changes (1d/7d), top-trader long/short positioning on Binance perps, and large on-chain transfers to/from exchange wallets above a USD threshold. The transfer feed covers ERC-20 tokens; for native assets (BTC, ETH) it substitutes market-wide USDT exchange flows as a dry-powder signal. Exchange withdrawals suggest accumulation; deposits suggest potential sell pressure. For specific whale wallets and their live positions use flow_whale_positions.

  ConnectorNo auth

• get_flights_bookings_bookingid_cancellationsA

  MAQAMI TravelB

  ## Overview Returns refund eligibility, estimated refund amounts, and penalty details for a booking **without actually cancelling it**. Useful before `post_flights_bookings_bookingid_cancellations` to understand the financial impact of cancellation. ## When to Use - **Pre-cancellation review** — Show the customer the potential maximum refund (not guaranteed) before they confirm cancellation - **Refund estimation** — Display potential maximum refund and penalty amounts in the booking management UI (refund is not granted until cancel completes) - **Eligibility check** — Determine whether the booking is within the void window (`isVoidable`) or eligible for a partial refund (`isRefundable`) ## What You Get - **`confidence`** — How reliable the quote is (`confirmed`, `estimated`, `heuristic`, `unknown`) - **`isRefundable` / `isVoidable`** — Quick eligibility flags - **`refund` / `penalty`** — Aggregate amounts with margin applied. `refund` is the potential maximum the airline may refund — not a granted/guaranteed amount - **`penalties[]`** — Itemised penalty breakdown when available - **`tickets[]`** — Per-ticket detail when available - **`destination`** — Where the refund goes - **`vouchers[]`** — Airline travel vouchers / credit-shells when `destination` is `voucher`; omitted when absent. Distinct from MAQAMI discount `voucherCode` on prebook ## Concurrent cancellation If a cancellation was already submitted and is still awaiting provider confirmation, this endpoint returns **HTTP 409** with code `49007` (`CONCURRENT_OPERATION`). A new quote is not available until that cancellation completes or fails. ## Refund amount caveat The `refund` amount on a cancellation quote is the **potential maximum** the airline may refund if cancellation proceeds under the quoted conditions. It is an estimate for decision-making only and is **not granted** — the final refund (if any) is determined when cancellation completes and may be lower or zero. The refund may arrive asynchronously once the airline determines the final amount. ## Key Features - **Non-destructive** — Does not cancel the booking; safe to call before user confirmation - **Margin-applied pricing** — All amounts (including voucher `pricing.display`) reflect the same margin applied at booking time ## Quick Start Provide the `bookingId` from the flight booking confirmation. Each call checks the airline live. Requires the `bookingId` and the `email` used to book: the server only returns or changes a booking when they match.

  ConnectorNo auth

• get_flights_bookings_bookingid_cancellationsA

  MAQAMI TravelB

  ## Overview Returns refund eligibility, estimated refund amounts, and penalty details for a booking **without actually cancelling it**. Useful before `post_flights_bookings_bookingid_cancellations` to understand the financial impact of cancellation. ## When to Use - **Pre-cancellation review** — Show the customer the potential maximum refund (not guaranteed) before they confirm cancellation - **Refund estimation** — Display potential maximum refund and penalty amounts in the booking management UI (refund is not granted until cancel completes) - **Eligibility check** — Determine whether the booking is within the void window (`isVoidable`) or eligible for a partial refund (`isRefundable`) ## What You Get - **`confidence`** — How reliable the quote is (`confirmed`, `estimated`, `heuristic`, `unknown`) - **`isRefundable` / `isVoidable`** — Quick eligibility flags - **`refund` / `penalty`** — Aggregate amounts with margin applied. `refund` is the potential maximum the airline may refund — not a granted/guaranteed amount - **`penalties[]`** — Itemised penalty breakdown when available - **`tickets[]`** — Per-ticket detail when available - **`destination`** — Where the refund goes - **`vouchers[]`** — Airline travel vouchers / credit-shells when `destination` is `voucher`; omitted when absent. Distinct from MAQAMI discount `voucherCode` on prebook ## Concurrent cancellation If a cancellation was already submitted and is still awaiting provider confirmation, this endpoint returns **HTTP 409** with code `49007` (`CONCURRENT_OPERATION`). A new quote is not available until that cancellation completes or fails. ## Refund amount caveat The `refund` amount on a cancellation quote is the **potential maximum** the airline may refund if cancellation proceeds under the quoted conditions. It is an estimate for decision-making only and is **not granted** — the final refund (if any) is determined when cancellation completes and may be lower or zero. The refund may arrive asynchronously once the airline determines the final amount. ## Key Features - **Non-destructive** — Does not cancel the booking; safe to call before user confirmation - **Margin-applied pricing** — All amounts (including voucher `pricing.display`) reflect the same margin applied at booking time ## Quick Start Provide the `bookingId` from the flight booking confirmation. Each call checks the airline live. Requires the `bookingId` and the `email` used to book: the server only returns or changes a booking when they match.

  ConnectorNo auth

• scan_contract_sourceA

  TanodA

  pactlint: Scan Solidity source code for security bugs before you deploy, review or depend on it. For a deployed verified contract use scan_contract_address. Runs solc, Slither and custom DeFi detectors (unchecked ERC-20 returns, zero slippage limits, oracle misuse, ERC-4626 inflation, signature replay, ...). Returns a JSON report (findings with severity, confidence, file:line and a fix) plus Markdown. Price: USD 0.25 up to 3,000 nSLOC, USD 0.75 up to 15,000; refused inputs are never charged. Free: 3 scans or 30 txpeek checks per IP per UTC day. Typically 1-5 s, up to about 30 s for a large project; at most 60 s; a full queue is a 503 with Retry-After (not charged). Automated and heuristic, not an audit: findings can be false positives and an empty report does not prove the code is free of bugs. Docs: https://tanod.dev/learn/smart-contract-scanner-api.html

  ConnectorNo auth