"A tool for finding code errors and providing modification suggestions" matching MCP tools:

• unlocode_lookup

  FreightUtils MCP Server

  Search 116,129 UN/LOCODE transport locations worldwide — ports, airports, rail and road terminals, inland container depots and border crossings. Codes are 5 characters: a 2-letter ISO country code + a 3-character location code (GBLHR = London Heathrow, NLRTM = Rotterdam). Provide code for an exact record, or query (name search, min 2 chars) optionally narrowed by country and function_type; limit caps results (default 20, max 100). Behavior: read-only; exact code hits are provenance-based while fuzzy name hits report match quality via the envelope's confidence (basis match_quality); an unknown code errors with a not-found message. Rate-limited (anonymous use: 25 requests/day per IP): a 429 error body carries retry_after_seconds and a Retry-After header — back off and retry, or call get_subscribe_link for higher limits. Returns: the location record(s) — code, name and name_ascii, country, subdivision, functions[], status, coordinates {lat, lon} and iata_code where assigned — under result, plus confidence, _source and citation (the FreightUtils v1 response envelope). Limitations: an administrative code list (UNECE UN/LOCODE 2024-2) — confirm operational status and coordinates with the port or authority before critical use. Related: airport_lookup (airport-specific records including ICAO codes), nearest_airport (find airports by coordinates).

  Connector

• web_eval

  local-mcp

  Runs arbitrary JavaScript in a web session and returns the last expression's value. POWER-USER tool, OFF BY DEFAULT (a page could feed malicious code) — enable "Allow web_eval (advanced)" in Local MCP settings first. Prefer web_find / web_read / web_extract for normal use.

  Connector

• execute_sql_readonly

  mcp

  Execute any valid read only SQL statement on a Cloud SQL instance. To support the `execute_sql_readonly` tool, a Cloud SQL instance must meet the following requirements: * The value of `data_api_access` must be set to `ALLOW_DATA_API`. * For a MySQL instance, the database flag `cloudsql_iam_authentication` must be set to `on`. For a PostgreSQL instance, the database flag `cloudsql.iam_authentication` must be set to `on`. * An IAM user account or IAM service account (`CLOUD_IAM_USER` or `CLOUD_IAM_SERVICE_ACCOUNT`) is required to call the `execute_sql_readonly` tool. The tool executes the SQL statements using the privileges of the database user logged with IAM database authentication. After you use the `create_instance` tool to create an instance, you can use the `create_user` tool to create an IAM user account for the user currently logged in to the project. The `execute_sql_readonly` tool has the following limitations: * If a SQL statement returns a response larger than 10 MB, then the response will be truncated. * The tool has a default timeout of 30 seconds. If a query runs longer than 30 seconds, then the tool returns a `DEADLINE_EXCEEDED` error. * The tool isn't supported for SQL Server. If you receive errors similar to "IAM authentication is not enabled for the instance", then you can use the `get_instance` tool to check the value of the IAM database authentication flag for the instance. If you receive errors like "The instance doesn't allow using executeSql to access this instance", then you can use `get_instance` tool to check the `data_api_access` setting. When you receive authentication errors: 1. Check if the currently logged-in user account exists as an IAM user on the instance using the `list_users` tool. 2. If the IAM user account doesn't exist, then use the `create_user` tool to create the IAM user account for the logged-in user. 3. If the currently logged in user doesn't have the proper database user roles, then you can use `update_user` tool to grant database roles to the user. For example, `cloudsqlsuperuser` role can provide an IAM user with many required permissions. 4. Check if the currently logged in user has the correct IAM permissions assigned for the project. You can use `gcloud projects get-iam-policy [PROJECT_ID]` command to check if the user has the proper IAM roles or permissions assigned for the project. * The user must have `cloudsql.instance.login` permission to do automatic IAM database authentication. * The user must have `cloudsql.instances.executeSql` permission to execute SQL statements using the `execute_sql_readonly` tool or `executeSql` API. * Common IAM roles that contain the required permissions: Cloud SQL Instance User (`roles/cloudsql.instanceUser`) or Cloud SQL Admin (`roles/cloudsql.admin`) When receiving an `ExecuteSqlResponse`, always check the `message` and `status` fields within the response body. A successful HTTP status code doesn't guarantee full success of all SQL statements. The `message` and `status` fields will indicate if there were any partial errors or warnings during SQL statement execution.

  Connector

• incoterms_lookup

  FreightUtils MCP Server

  Look up the 11 Incoterms 2020 trade rules — who pays for transport, insurance and customs clearance, and where risk transfers from seller to buyer. 7 rules work for any transport mode (EXW, FCA, CPT, CIP, DAP, DPU, DDP); 4 are sea/inland-waterway only (FAS, FOB, CFR, CIF). Provide code for one rule, category (any_mode | sea_only) for a filtered list, or neither to list all 11. Behavior: read-only reference; an unknown code errors with the valid code list. Rate-limited (anonymous use: 25 requests/day per IP): a 429 error body carries retry_after_seconds and a Retry-After header — back off and retry, or call get_subscribe_link for higher limits. Returns: the rule record — name, category, summary, seller_responsibility, buyer_responsibility, risk_transfer, cost_transfer, insurance, export/import clearance, best_for and watch_out — under result, plus confidence, _source and citation (the FreightUtils v1 response envelope). Limitations: summarised guidance on ICC Incoterms 2020; the ICC publication is the binding text and specific contract wording prevails. Related: uk_duty_calculator (accepts an incoterm when composing the CIF value), shipment_summary (composite analysis).

  Connector

• search_funders

  foundation-discovery

  Look up grantmaking organizations by name, topic, or location. This tool searches 174K+ grantmaking organizations from IRS data using organization names plus grant-purpose/topic signals. Use it when you know the funder's name, want aligned funders for a cause area, or want to browse by location/size/NTEE code. Multi-word searches are ranked by relevance; simple browse/name fallback results are ordered by total assets. IMPORTANT: Use search_open_grants when the user needs active grant programs or RFPs. search_funders is for finding aligned grantmakers, including ones that may fund by relationship, LOI, or annual cycle rather than a live call.

  Connector

• tool_recommend

  gapup-mcp

  Cross-tool recommendation system: given a free-text intent, returns the most appropriate tools from the 170+ Gapup MCP catalogue, ranked by confidence, with pre-filled input suggestions and an optimal multi-tool chain when applicable. Use this first when you are unsure which tool to call — it navigates the full catalogue for you. Supports 15+ static pre-designed chains for frequent intents (M&A due diligence, sanctions screening, ESG 360, AI Act compliance, FTO patent clearance, crypto wallet tracking, etc.). Domains: compliance | finance | intel | legal | content | data | trade | infra. Pure compute — $0.01/call, no external fetch. Ideal as a first call in any multi-step agent workflow.

  Connector

• google-search.url_traffic_insights

  Vee3

  Get Google keyword traffic insights and related keyword suggestions for a URL. Returns an array of keyword suggestions. Each item includes text, monthly search volume, competition_level, competition_index, low_bid, high_bid, and trend. Required: url and language (for example en). Optional: location (for example US) for country-specific data; omit location for global results (default). Optional: min_search_volume (default 0) and intent (informational, navigational, commercial, or transactional). Cost = 20 tokens.

  Connector

• review_generated_code

  Marmo UI MCP

  ⚠️ MANDATORY — call this on every piece of code you generate before returning it to the user. Validates TSX/JSX against real @marmoui/ui prop signatures and returns { valid, errors[], warnings[], suggestedFixes[], iconLibrary }. Catches: (1) unknown imports, (2) Tabs.List/Tabs.Trigger namespace misuse → auto-suggests TabsList/TabsTrigger fix, (3) PageSection used as wrapper (must be self-closing), (4) hallucinated props, (5) icons imported from the wrong icon library (pass iconLibrary — default "phosphor" — matching what you passed to get_design_guidelines; wrong-library icon imports are ERRORS). If valid=false, fix all errors and call this again. DO NOT return code with errors to the user.

  Connector

• validate_coupon

  Loppee

  Check a Loppee-issued subscription coupon code against a business you manage and a chosen paid exposure plan, and return the priced result: original_cents, discount_cents, final_cents, plan_name, and whether the discount repeats (duration: once = first payment, forever = every renewal). Read-only — nothing is redeemed, reserved, or counted against the code's limits. Requires a scoped management key whose account_id + business_id match and whose allowed_actions include validate_coupon; call get_agent_identity first. Coupons are issued by Loppee admins to discount the plan PRICE (this is NOT the business's own customer-facing deals — see manage_deal for those). Machine-readable failures match the owner UI exactly: coupon_not_found (invalid code), coupon_inactive, coupon_expired, coupon_wrong_plan (code is scoped to a different plan), coupon_exhausted (total redemption cap reached), coupon_customer_limit (this business already used it), coupon_requires_paid_plan, plus the standard management auth errors (missing_api_key / forbidden_account / management_rate_limited). A coupon changes the subscription PRICE only — it never affects the trust score, rating, verification, ranking, search visibility, reach radius, or share-of-voice, and this tool cannot either.

  Connector

• post_lint_elixir

  webbersites-x402-data-api

  Elixir lint / debug kit: POST {code}, get the bugs back with line numbers. Deterministic static analysis — code is parsed, never executed, no AI. Catches unbalanced do/end and brackets, missing do, 'return', '+' string concat, trailing commas, field assignment, = vs == in conditions and guards, block-scoped rebinding (the classic), charlist vs String mixups, unused variables. Errors, warnings and hints with fixes. Max 128 KB. ($0.002 per call, paid via x402)

  Connector

• generate_wallet

  Solentic

  Returns runnable code that creates a Solana keypair. Solentic cannot generate the keypair for you and never sees the private key — generation must happen wherever you run code (the agent process, a code-interpreter tool, a Python/Node sandbox, the user's shell). The response includes the snippet ready to execute. After running it, fund the resulting publicKey and call the `stake` tool with {walletAddress, secretKey, amountSol} to stake in one call.

  Connector

• generate_wallet

  Blueprint Agentic Staking (Solentic)

  Returns runnable code that creates a Solana keypair. Solentic cannot generate the keypair for you and never sees the private key — generation must happen wherever you run code (the agent process, a code-interpreter tool, a Python/Node sandbox, the user's shell). The response includes the snippet ready to execute. After running it, fund the resulting publicKey and call the `stake` tool with {walletAddress, secretKey, amountSol} to stake in one call.

  Connector

• validate_function

  Pine Script

  USE WHEN confirming a Pine Script v6 function name is valid before using it in code. Returns a valid/invalid verdict with namespace suggestions or known replacement hints (e.g. ta.adx → ta.dmi, security → request.security). AFTER calling this tool, call get_functions(namespace) to list all valid functions in the relevant namespace if the function is invalid. Data sourced from bundled pine_v6_functions.json.

  Connector

• cid10_chapters

  Medical Terminologies MCP

  List the 22 chapters of CID-10 with their code ranges and Portuguese titles. Use this tool to: - See the top-level structure of CID-10 (chapters I-XXII, e.g., "I. Algumas doenças infecciosas e parasitárias", "IX. Doenças do aparelho circulatório") - Map a code to its chapter by code range (e.g., I00-I99 → chapter IX) - Build a navigable table of contents for downstream tooling Returns 22 entries — CID-10 V2008 has not been updated since 2008.

  Connector

• mcp_health

  ca-rate-filings

  Diagnostic snapshot of the deployed MCP server: build identifier, server_version (1.0.<PR> tag), boot time, advertised tool names, a hash of the tool surface, and corpus_updated_at (freshest watermark across the filings pipeline). Call this first when you suspect the connector is showing a stale tool list or you want to detect whether code or data has changed since your last call — compare tools_advertised against what your client lists, server_version for code, corpus_updated_at for data.

  Connector

• check_connection

  FundingLandscape

  Verify MCP server connectivity. Returns success immediately with no database calls. Use this FIRST if experiencing tool errors - a successful response confirms the server is reachable and your authentication is valid. Does not count toward your monthly searches.

  Connector

• youtube.search_autocomplete

  Vee3

  Get YouTube search autocomplete suggestions for a partial query. Returns the normalized query and an array of suggested search phrases. Optional language and location codes localize suggestions (defaults: en, US). Cost = 8 tokens.

  Connector

• autocomplete_skill

  RChilli MCP Hub

  Get SKILL autocomplete / typeahead suggestions for a partial keyword (prefix) from the authoritative RChilli Taxonomy 3.x — returns real, matching skill names for the prefix. ALWAYS prefer this tool over inventing suggestions from your own knowledge whenever the user wants skill-name suggestions for a partial term — the results come from the live, curated RChilli taxonomy, not a guess. Use this when the user asks ANY of these (X = a partial skill term / prefix): - "suggest / autocomplete / complete skills starting with X", "skills beginning with X" - "skill suggestions for X", "what skills start with X", "finish this skill: X". Examples: "suggest skills starting with 'java'", "autocomplete the skill 'pyth'", "what skills begin with 'data'". Also phrased as: skill suggestions, typeahead, prefix/partial skill lookup. Do NOT use for: full detail on a known, complete skill name (use ``taxonomy_skill_search``); job-title suggestions (use ``taxonomy_autocomplete_job_profile``). Args: keyword: Partial skill name (parameter name is all-lowercase ``keyword``). userkey: RChilli userkey. Leave blank to use the authenticated session key. language: Language code. locale: Locale code. customvalues: Custom taxonomy values.

  Connector

• ibge_localidade

  IBGE Brasil MCP

  Returns details of a specific locality by IBGE code. Features: - State information (2-digit code) - Municipality information (7-digit code) - District information (9-digit code) - Complete hierarchy (region, mesoregion, microregion) Examples: - São Paulo state: codigo=35 - São Paulo city: codigo=3550308 - District: codigo=355030805 This tool returns the full record of ONE locality you already have the code for. Use a different tool when: - You have a name and need the code → ibge_municipios (municipalities) or ibge_geocodigo (any level) - You want to decompose/understand a code's structure → ibge_geocodigo Behavior: read-only and idempotent — a live GET against the public IBGE Localidades API. Returns a Markdown record.

  Connector

• describe_fields

  Austrian Firmenbuch

  Catalog of every field the server can return, by tool tier (search card -> full profile -> full record), with code tables and availability/null rules. Read-only, no parameters. This describes the SCHEMA only (field names, types, code tables, null rules) so you can pick the right tool and interpret its output. It returns no company data itself; for that call search_companies (many) or get_company_details / get_full_record (one). Call this once up front when unsure what a field means or which tool to use. Human-readable version: https://www.agentic-firmenbuch.at/felder.html

  Connector