"Running MySQL Queries Through a MySQL Socket" matching MCP tools:

• generate_migration

  ThinAir Data

  Generate dialect-correct ALTER TABLE migration SQL + rollback from a plain-English intent. Output uses the connection's exact dialect (ALTER TABLE for all three, plus pg-specific `USING` casts / mssql-specific `sp_rename` / mysql-specific `MODIFY COLUMN`). Never executes. Check response `dialect` field before manually editing — don't hand-translate across dialects. [BUILD tier]

  Connector

• compare

  XFMS — Xpansion Framework Model Source

  Run a live A/B test between 2–5 user-specified models for a stated purpose. NO ranking step — the supplied model_ids ARE the candidate set. Generates 5 representative test queries from the purpose, runs them through every named model in parallel, and returns real cost, latency, and plain-English commentary on who won what. Unknown IDs are dropped with a note; if fewer than 2 IDs resolve, the call refuses. Use this whenever the user names specific models to compare (e.g. 'A/B test X and Y'). For engine-chosen candidates, use `benchmark` instead. Costs more than `rank` (10+ live LLM calls). Free-tier note: when any candidate ends in ':free', the probe is capped at 3 queries (no adaptive expansion) because free-tier rate limits often push longer probes past the deploy's 5-minute ceiling — evidence will be shallower. The commentary surfaces this when it happens.

  Connector

• dossier_ct_log

  drwho.me developer tools

  Core dossier check: Discover subdomains visible in Certificate Transparency logs. Use for attack-surface mapping; prefer dossier_full when running a complete audit. Queries crt.sh first, falls back to certspotter; capped at 100 unique subdomains; 10s timeout. Returns a CheckResult with { subdomains[], wildcards[], certCount, source }.

  Connector

• cross_db_query

  ThinAir Data

  ⚠️ SQL MUST BE VALID IN EVERY DIALECT YOU TARGET — stick to ANSI-ish SELECT syntax when mixing pg/mysql/mssql. `SELECT TOP 10` (mssql) or `LIMIT` (others) will fail on the wrong side. Run the same query across 2-4 connections in parallel; returns per-connection rows + errors for diffing. Canonical use cases: regional compare (`['mssql-reporting-us', 'mssql-reporting-eu']`), cross-dialect sync check (`['prod-postgres-fleet', 'prod-mysql-app']`), 3-env drift, 4-region compare. Resolve every connection name via `list_connections` first; tool fails per-connection on unknown names. ARCHITECT-tier cap: 4 connections; https://www.thinair.co/ for unlimited. [ARCHITECT tier]

  Connector

• resolve_names

  mcp

  Resolves a batch list of specific location queries (landmark names or exact addresses) into canonical Google Maps Place IDs. **Input Requirements (CRITICAL):** 1. **`queries` (array of objects - MANDATORY):** A list of location queries to resolve. You may specify up to 20 queries. * **Each query object must have:** * **`text` (string - MANDATORY):** The text query representing a specific place name or address to resolve. * **Examples:** `'Googleplex, Mountain View, CA'`, `'1600 Amphitheatre Pkwy, Mountain View, CA'`, `'Eiffel Tower, Paris'`. 2. **`location_bias` (object - OPTIONAL):** Use this to prioritize results near a specific geographic area. * **Format:** `{"viewport": {"low": {"latitude": [value], "longitude": [value]}, "high": {"latitude": [value], "longitude": [value]}}}` 3. **`region_code` (string - OPTIONAL):** The Unicode CLDR region code (two-letter country code, e.g., `US`, `CA`) of the user to bias the results. **Instructions for Tool Call:** * Specificity (CRITICAL): Queries must represent a specific place name or address. General searches like `'restaurants'` or chain names like `'Starbucks'` are not supported. * Do NOT call this tool if the downstream tools you plan to invoke already accept raw address or place name strings directly. **Error Handling (CRITICAL):** * This is a batch processing tool. A request might return "mixed results" (e.g. some queries resolve successfully while others fail). * The output list of `results` is guaranteed to map 1:1 with the input `queries` indices. A failed query will result in an empty `Result` message (no `entity` is set) at its corresponding index in the `results` list. * You **MUST** check the `failed_requests` map field in the response to identify which specific query index failed. The key of `failed_requests` represents the 0-based index of the failed query in the request. Do not assume the entire batch call failed because of a partial failure.

  Connector

• dossier_ct_log

  drwho.me

  Core dossier check: Discover subdomains visible in Certificate Transparency logs. Use for attack-surface mapping; prefer dossier_full when running a complete audit. Queries crt.sh first, falls back to certspotter; capped at 100 unique subdomains; 10s timeout. Returns a CheckResult with { subdomains[], wildcards[], certCount, source }.

  Connector

• resolve_names

  Google Maps

  Resolves a batch list of specific location queries (landmark names or exact addresses) into canonical Google Maps Place IDs. **Input Requirements (CRITICAL):** 1. **`queries` (array of objects - MANDATORY):** A list of location queries to resolve. You may specify up to 20 queries. * **Each query object must have:** * **`text` (string - MANDATORY):** The text query representing a specific place name or address to resolve. * **Examples:** `'Googleplex, Mountain View, CA'`, `'1600 Amphitheatre Pkwy, Mountain View, CA'`, `'Eiffel Tower, Paris'`. 2. **`location_bias` (object - OPTIONAL):** Use this to prioritize results near a specific geographic area. * **Format:** `{"viewport": {"low": {"latitude": [value], "longitude": [value]}, "high": {"latitude": [value], "longitude": [value]}}}` 3. **`region_code` (string - OPTIONAL):** The Unicode CLDR region code (two-letter country code, e.g., `US`, `CA`) of the user to bias the results. **Instructions for Tool Call:** * Specificity (CRITICAL): Queries must represent a specific place name or address. General searches like `'restaurants'` or chain names like `'Starbucks'` are not supported. * Do NOT call this tool if the downstream tools you plan to invoke already accept raw address or place name strings directly. **Error Handling (CRITICAL):** * This is a batch processing tool. A request might return "mixed results" (e.g. some queries resolve successfully while others fail). * The output list of `results` is guaranteed to map 1:1 with the input `queries` indices. A failed query will result in an empty `Result` message (no `entity` is set) at its corresponding index in the `results` list. * You **MUST** check the `failed_requests` map field in the response to identify which specific query index failed. The key of `failed_requests` represents the 0-based index of the failed query in the request. Do not assume the entire batch call failed because of a partial failure.

  Connector

• compare

  XFMS — Model Source

  Run a live A/B test between 2–5 user-specified models for a stated purpose. NO ranking step — the supplied model_ids ARE the candidate set. Generates 5 representative test queries from the purpose, runs them through every named model in parallel, and returns real cost, latency, and plain-English commentary on who won what. Unknown IDs are dropped with a note; if fewer than 2 IDs resolve, the call refuses. Use this whenever the user names specific models to compare (e.g. 'A/B test X and Y'). For engine-chosen candidates, use `benchmark` instead. Costs more than `rank` (10+ live LLM calls). Free-tier note: when any candidate ends in ':free', the probe is capped at 3 queries (no adaptive expansion) because free-tier rate limits often push longer probes past the deploy's 5-minute ceiling — evidence will be shallower. The commentary surfaces this when it happens.

  Connector

• get_app_status

  BorealHost

  Get app installation status and log. Poll this after install_app() to track progress. Requires: API key with read scope. Args: slug: Site identifier app_id: App ID from install_app() response Returns: {"id": "uuid", "app_name": "forge", "status": "running"|"installing"|"failed", "install_log": "..."} Statuses: "installing", "running", "stopped", "failed", "uninstalled"

  Connector

• devloop_record_sandbox

  Keploy

  Record mocks for V1 repo-mode API tests using the V1-native CLI command `keploy sandbox local record`. Runs the dev's app under the keploy eBPF agent, drives the V1 chained-CRUD tests from `keploy/api-tests/<resource>/test.yaml`, captures every outbound call (DB queries, Redis ops, downstream HTTP) as mocks, and lays them out at `<app_dir>/keploy/<suite-name>/{tests/, mocks.yaml, config.yaml}` in the standard OSS test-set tree. On success, mocks upload to the Keploy canonical pool by content hash; the hash lands in config.yaml so a teammate's later replay fetches the same bytes. CRITICAL — DO NOT CONFUSE WITH `keploy record sandbox`: * `keploy sandbox local record` (V1, repo-mode) ← this is what the playbook below uses * `keploy record sandbox` (legacy, cloud-mode) ← DO NOT call this for V1 The two are entirely different commands. Cloud-mode requires server-side suites (queried via --suite-ids) — V1 repo-mode reads tests from the local filesystem and never registers them in the cloud. If the dev is in repo storage mode (verify via devloop_resolve_storage's source=persisted, mode=repo), V1 is the ONLY correct sandbox path. STRICT — TIME-FREEZING DOES NOT APPLY TO RECORD. Recording MUST use the dev's regular (prod) Dockerfile or native binary. NEVER spawn the app via Dockerfile.keploy / "-f docker-compose.keploy.yml" / "-tags=faketime" build during record. The faketime binary writes wrong timestamps into captured mocks (it reads time from the offset file, not the wall clock) and the entire capture becomes corrupt — recovery requires re-recording from scratch with the prod binary. If a previous replay failed with expired-JWT and the dev wants to "fix" it, the fix is to re-RUN the replay with --freezeTime, NOT to re-record. The recorded mocks captured against the prod binary are exactly what replay's clock-rewind is designed to validate; touching the record path defeats the whole mechanism. ONLY call this with an explicit dev opt-in. The valid triggers: * Dev directly asks ("capture mocks", "sandbox record", "rerecord the users mocks"). * Post-resource menu (Step 5 of devloop_generate_resource_flow) — dev picks "Capture mocks so CI runs in seconds". * get_session_report shows mock_mismatch_dominant=true AND the dev says yes to your "rerecord?" prompt. Pre-conditions: * Dev's app must NOT already be running (keploy spawns its own copy of the app under the agent's eBPF hooks via the -c command). If a server is up at the target port, KILL IT first or the agent's network capture won't see the traffic. * Real downstream deps (MySQL, Redis, Kafka, etc.) MUST be running — the capture proxies through to them on first contact so the recorded mocks contain real responses. * The test YAML must exist at <app_dir>/keploy/api-tests/<resource>/test.yaml. Returns a playbook for `keploy sandbox local record` with the V1 flag surface: --test-dir, --app-url, -c (spawn command), --container-name (docker-compose only), --skip-mock-upload (offline), --skip-report-upload (offline). Mocks land per-suite at keploy/<suite-name>/. NDJSON progress at --progress-file for the standard tail-til-done loop.

  Connector

• instances_list

  mcp

  Retrieve all running VM instances for the authenticated account. Sensitive credentials (e.g. cleartext VM password) are redacted; fetch them through the REST API if needed.

  Connector

• get_scan_status

  Cookie Consent Compliance Scanner

  Check whether a scan is still running. Poll this every 10–15 seconds after calling scan_url. When done=True, call get_scan_report or get_failing_checks to retrieve results.

  Connector

• cancel_bounty

  TaskBounty

  Cancels an unfunded draft. Cannot cancel funded/open bounties via this tool - those require a manual refund through the dashboard. Requires a TaskBounty API key.

  Connector

• timer

  todo.vu

  Manage the running timer for the current user in a workspace. A user can have one timer running per workspace. All operations return the list of active timers in the workspace. Args: workspace_id: Workspace slug (required). operation: One of: - 'start': Start the timer. Optionally set task_id, timer_started, and description. - 'stop': Stop the running timer and emit a time entry. Optionally pass task_id to override the task, or pause=True to pause without clearing the task. - 'change': Update the running timer. Supply any of task_id, description, timer_started — only the provided fields are updated. - 'discard': Discard the running timer without saving a time entry. - 'list': Return current active timers (no changes made). task_id: Task ID to associate with the timer. Used by start, stop, and change. description: Timer description. Used by start and change. timer_started: ISO 8601 datetime string for when the timer started, e.g. '2026-03-12T09:00:00' (in the user's local timezone). Used by start and change. pause: If True, pause the timer (keeps task ID but clears start time). Only valid for stop.

  Connector

• install_app

  BorealHost

  Install an app template on a VPS/Cloud site. Starts a background installation. Poll get_app_status() for progress. Requires: API key with write scope. VPS or Cloud plan only. Args: slug: Site identifier template: App template slug. Available: django, laravel, nextjs, nodejs, nuxtjs, rails, static, forge app_name: Short name for the app (2-50 chars, lowercase alphanumeric + hyphens). Used as subdomain: {app_name}.{site_domain} db_type: Database type. "none", "mysql", or "postgresql" (depends on template) domain: Custom domain override (default: {app_name}.{site_domain}) display_name: Human-friendly name (default: derived from app_name) Returns: {"id": "uuid", "app_name": "forge", "status": "installing", "message": "Installation started. Poll for progress."} Errors: FORBIDDEN: Plan does not support apps (shared plans) VALIDATION_ERROR: Invalid template, app_name, or duplicate name

  Connector

• import_data

  mcp

  Import data into a Cloud SQL instance. If the file doesn't start with `gs://`, then the assumption is that the file is stored locally. If the file is local, then the file must be uploaded to Cloud Storage before you can make the actual `import_data` call. To upload the file to Cloud Storage, you can use the `gcloud` or `gsutil` commands. Before you upload the file to Cloud Storage, consider whether you want to use an existing bucket or create a new bucket in the provided project. After the file is uploaded to Cloud Storage, the instance service account must have sufficient permissions to read the uploaded file from the Cloud Storage bucket. This can be accomplished as follows: 1. Use the `get_instance` tool to get the email address of the instance service account. From the output of the tool, get the value of the `serviceAccountEmailAddress` field. 2. Grant the instance service account the `storage.objectAdmin` role on the provided Cloud Storage bucket. Use a command like `gcloud storage buckets add-iam-policy-binding` or a request to the Cloud Storage API. It can take from two to up to seven minutes or more for the role to be granted and the permissions to be propagated to the service account in Cloud Storage. If you encounter a permissions error after updatingthe IAM policy, then wait a few minutes and try again. After permissions are granted, you can import the data. We recommend that you leave optional parameters empty and use the system defaults. The file type can typically be determined by the file extension. For example, if the file is a SQL file, `.sql` or `.csv` for CSV file. The following is a sample SQL `importContext` for MySQL. ``` { "uri": "gs://sample-gcs-bucket/sample-file.sql", "kind": "sql#importContext", "fileType": "SQL" } ``` There is no `database` parameter present for MySQL since the database name is expected to be present in the SQL file. Specify only one URI. No other fields are required outside of `importContext`. For PostgreSQL, the `database` field is required. The following is a sample PostgreSQL `importContext` with the `database` field specified. ``` { "uri": "gs://sample-gcs-bucket/sample-file.sql", "kind": "sql#importContext", "fileType": "SQL", "database": "sample-db" } ``` The `import_data` tool returns a long-running operation. Use the `get_operation` tool to poll its status until the operation completes.

  Connector

• get_stats

  Velvoite — EU Financial Regulatory Compliance

  Get an overview of the Velvoite regulatory corpus. Returns document counts by source, regulation family, entity type, urgency distribution, obligation summary, and date range. Call this FIRST to orient yourself before running queries. No parameters needed.

  Connector

• openstreetmap_query_raw

  openstreetmap-mcp-server

  Execute a raw Overpass QL query for advanced spatial queries that the convenience tools do not cover. Use for multi-type queries, union queries, relation membership, historical queries, or any operation requiring full Overpass QL expressiveness. The query must include [out:json]. Example: "[out:json][timeout:15];node[\"natural\"=\"peak\"](47.5,-122.5,47.7,-122.2);out body;" Validate complex queries at overpass-turbo.eu before use. For simple "what's near X?" or "what's in this area?" queries, use openstreetmap_query_nearby or openstreetmap_query_bbox instead.

  Connector

• get_scan_status

  Waivern Cookie Consent Analyser

  Check whether a scan is still running. Poll this every 10–15 seconds after calling scan_url. When done=True, call get_scan_report or get_failing_checks to retrieve results.

  Connector

• search_semantic

  Tripitaka MCP (hosted)

  Semantic search — match by meaning, not exact words. Uses vector similarity (cosine distance) over `text_pali` embedded with a multilingual MiniLM model. 🤔 **In most cases you should use `search_hybrid` instead** — it combines this semantic search with keyword search and ranks better. Use this tool only when you need: - Pure semantic results (no keyword influence) - Fine-grained `threshold` tuning (hybrid uses RRF which is harder to tune) - To debug what semantic alone picks up vs keyword ⚠️ Known limitations: - The index is **Pāli only** (English/Thai queries pass through the multilingual embedding but the model isn't tuned on Pāli) - English queries usually embed better than Thai (model is EN-primary) - For specific Pāli terms (`appamāda`, `dukkha`), exact match is better — use `search_by_keyword` instead - Pāli stock phrases recur in many suttas → similarity scores cluster; read the top 10, don't trust rank 1 alone

  Connector