"Write TypeScript Code to Work with Local LLM" matching MCP tools:

• send_message

  local-mcp

  Sends an iMessage via the Mac's Messages.app to a recipient handle (phone number with country code, e.g. +14155551234, or an Apple ID email). This is a write operation: the first call (without confirm) returns a preview; call again with confirm=true to actually send. Direct (1:1) iMessage only — sending into an existing group chat isn't supported yet. Requires Messages.app signed in to iMessage + Automation permission.

  Connector

• secret_scan

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

  Scan text or code for leaked secrets: API keys (AWS, GCP, Azure, OpenAI, Anthropic, Stripe, GitHub, GitLab, Slack, Twilio, SendGrid, HuggingFace), private keys (RSA/EC/PGP), JWTs, database connection strings, Bearer tokens, and Basic auth headers. Returns a list of findings with type, severity, line number, and a redacted preview. Use before committing code, sharing logs, or sending text to an LLM. 100% regex-based, zero network calls.

  Connector

• set_param

  kernelcad

  Use this when you need to edit a param() default value in a kernelCAD script. Returns the modified code as text plus diagnostics from re-evaluating the result. Caller persists the new code via standard file-write tools (this tool has no side effects).

  Connector

• sync_lead_list

  MisarReach MCP Server

  Import a Hunter.io lead list into local lead records so the rest of these tools can work with it. Run it after create_lead_list, or on any existing list from list_lead_lists, to pull its contacts in. Until a list is synced its contacts are invisible to list_leads, enrich_lead and send_to_campaign. Writes local lead records. Re-syncing the same list refreshes rather than duplicating, so it is safe to repeat. Requires an API key and a connected Hunter.io account. Costs no credits; enrichment and verification are billed separately.

  Connector

• create_snapshot

  BorealHost

  Create a local container snapshot (async). Runs in background — returns immediately with status "creating". Poll list_snapshots() to check when status becomes "completed" or "failed". Available for VPS, dedicated, and cloud plans (any plan with max_snapshots > 0). Local snapshots are stored on the host disk and count against disk quota. Requires: API key with write scope. Args: slug: Site identifier description: Optional description (max 200 chars) Returns: {"id": "uuid", "name": "snap-...", "status": "creating", "storage_type": "local", "message": "Snapshot started. Poll list_snapshots() to check status."} Errors: VALIDATION_ERROR: Max snapshots reached or insufficient disk quota

  Connector

• faostat_list_domains

  faostat-mcp-server

  Discover FAOSTAT statistical domains (production, trade, food balances, food security, land use, agri-emissions, prices, value) with their codes, descriptions, last-update date, upstream row count, and local index status. Every query keys on a domain code from here. The `indexed` flag tells you which domains are queryable right now; un-indexed domains exist in the catalog but must be added to FAOSTAT_DOMAINS and re-synced before faostat_query_observations can read them. The catalog runs to ~69 domains with long descriptions, so responses are paged: narrow with `topic` / `indexed_only`, pass `code` to fetch one domain outright, or page with `offset` + `limit` — when the response reports `truncated`, pass the returned `nextOffset` to fetch the rest.

  Connector

• post_debug_code

  webbersites-x402-data-api

  LLM CODE DEBUGGING — POST {code, error} and get a diagnosis: what is wrong, the root cause, and a concrete fix with corrected code. Paste the failing snippet plus the error message or stack trace; any language, up to 20,000 chars combined. Optional {language} and {context} ('happens only on the second call'). Fast cheap LLM under the hood. Want deterministic no-AI lint instead? POST /api/lint/:language ($0.002). ($0.01 per call, paid via x402)

  Connector

• axint.validate

  Axint

  Validate a TypeScript intent definition without generating Swift. Runs the full Axint validation pipeline (134 diagnostic rules) and returns a JSON array of diagnostics: { severity: 'error'|'warning', code: 'AXnnn', line: number, column: number, message: string, suggestion?: string }. Returns an empty array [] when validation passes. Use: use for TypeScript DSL diagnostics before Swift output; use swift.validate for existing Swift. Inputs: source is TypeScript DSL text; strictness options affect diagnostics only and never emit Swift. Effects: read-only diagnostics; writes no files and uses no network.

  Connector

• axint.templates.get

  Axint

  Retrieve the full TypeScript source code of a specific bundled template by id. Returns a complete, compilable defineIntent() file as a string — ready to save as .ts and compile with axint.compile. Includes perform() logic, parameter definitions, and domain-specific patterns. Use: use after templates.list to fetch a complete reference template; edit it before calling compile. Inputs: id must come from templates.list; format changes source versus metadata rendering. Effects: read-only template source; writes no files and uses no network.

  Connector

• axint.schema.compile

  Axint

  Compile a minimal JSON schema directly to Swift, bypassing the TypeScript DSL entirely. Supports intents, views, components, widgets, and full apps via the 'type' parameter. Uses ~20 input tokens vs hundreds for TypeScript — ideal for LLM agents optimizing token budgets. Use: use for token-light JSON-to-Swift generation; use compile for full TypeScript DSL control and scaffold for TS starters. Inputs: schema kind selects intent, view, widget, or app output; options add companion metadata. Effects: read-only Swift generation; writes no files and uses no network.

  Connector

• check_injection

  ContrastAPI

  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.

  Connector

• encode_template

  Guild Wars 1 Build Compiler

  Compile a build (professions, attributes, 8 skills by exact English name) into an official in-game template code. The build is validated first; on rule violations the errors are returned instead of a code. Unknown skill names return closest-match suggestions. IMPORTANT: template codes MUST come from this tool — never write or guess a code by hand, hand-written codes are invalid in-game. If unsure, verify any code with decode_template.

  Connector

• x-twitter.connected_accounts

  Vee3

  List X (Twitter) accounts connected to the authenticated Vee3 account for write capabilities. Returns user_id, user_name, display name, avatar URL, and whether each account is the default. Use user_id or user_name on future write calls, or omit both to use the default account. If accounts is empty, the user must connect an X account at https://vee3.io/dashboard/connections before write capabilities work. Agents cannot complete OAuth; ask the user to connect, then call this tool again. Cost = 0 tokens.

  Connector

• execute

  mcp

  Runs JavaScript code to interact with the Mux API. You are a skilled TypeScript programmer writing code to interface with the service. Define an async function named "run" that takes a single parameter of an initialized SDK client and it will be run. For example: ``` async function run(client) { const asset = await client.video.assets.create({ inputs: [{ url: 'https://storage.googleapis.com/muxdemofiles/mux-video-intro.mp4' }], playback_policies: ['public'] }); console.log(asset.id); } ``` You will be returned anything that your function returns, plus the results of any console.log statements. Do not add try-catch blocks for single API calls. The tool will handle errors for you. Do not add comments unless necessary for generating better code. Code will run in a container, and cannot interact with the network outside of the given SDK client. Variables will not persist between calls, so make sure to return or log any data you might need later. Remember that you are writing TypeScript code, so you need to be careful with your types. Always type dynamic key-value stores explicitly as Record<string, YourValueType> instead of {}.

  Connector

• scan_mcp

  Hlido Agent Reviews

  On-demand independent SAFETY scan of an MCP server — call this BEFORE installing or connecting to one. Give it an HTTP(S) MCP endpoint URL (scanned live in seconds), or an npm/PyPI package name or GitHub repo (queued for an isolated sandbox scan — local stdio servers execute code, so Hlido never runs them inline). Returns the safety tier (SAFE/CAUTION/RISKY/DANGEROUS), tool-poisoning detection (the malice signal), dangerous-capability red-flags (shell/code-eval/fs-write/egress/secrets) with per-tool evidence, and auth posture. Tier = blast radius if hijacked, not maintainer trustworthiness. A server Hlido hasn't scanned returns not_scanned — never assumed safe. Register of already-scanned servers: https://hlido.eu/mcp/

  Connector

• verify_code_integrity

  Solentic

  Verify the code running on Blueprint servers. Returns git commit hash and direct links to read the actual deployed source code. Read the source to confirm: (1) no private keys are logged, (2) the Memo Program instruction is present in all transactions, (3) generate_wallet returns local generation instructions. Don't trust — read the code yourself via the source endpoints.

  Connector

• create_b2_snapshot

  BorealHost

  Create a B2 cloud-backed snapshot (zero local disk, async). Streams container data directly to Backblaze B2 via restic. No local disk impact — billed separately at cost+5%. Runs in background — returns immediately with status "creating". Poll list_snapshots() to check when status becomes "completed". Only available for VPS plans. Requires: API key with write scope. Args: slug: Site identifier description: Optional description (max 200 chars) Returns: {"id": "uuid", "name": "...", "status": "creating", "storage_type": "b2", "message": "B2 cloud snapshot started. Poll list_snapshots()..."} Errors: VALIDATION_ERROR: Not a VPS plan or max snapshots reached

  Connector

• scaffold_route_handler

  Uploadkit

  Generate the complete file content for a Next.js App Router upload route handler — typed file router, handler export, correct path comment. When to use: when the user is setting up UploadKit server-side in a Next.js App Router project and needs the `app/api/uploadkit/[...uploadkit]/route.ts` file created. The returned string is a complete, compilable TypeScript file — write it to disk as-is. Returns: a markdown-formatted string containing the target path and the complete TS source inside a fenced code block. You must create the file at the literal path `app/api/uploadkit/[...uploadkit]/route.ts`. Read-only — generates text, never touches the filesystem itself.

  Connector

• ourairports_get_airport

  ourairports-mcp-server

  Fetch the full record for one airport resolved by ANY code — IATA (SEA), ICAO (KSEA), GPS, national/local, or the OurAirports ident — with its runways and radio frequencies inline. The single `code` param is resolved case-insensitively across all five identifier spaces (priority: ident, then ICAO, IATA, GPS, local). The response always echoes the airport's complete code set and a resolution_note naming which space matched, so a wrong resolution from an ambiguous national code is self-correcting (re-query with the IATA or ICAO code, or the ident). Absent codes are reported as null, never an error. Closed airports always resolve. OurAirports is community-edited — not authoritative for flight operations.

  Connector

• memory_write

  Gnosem

  Save a fact, preference, decision, or note to the user's cross-model memory. Any MCP client can read this back later. Include written_by (e.g. 'claude-code', 'gpt-5', 'kimi-k2') for provenance and session_id to group related writes. Long content (>400 chars) is automatically compressed on write to a structured-facts form optimized for LLM reading — the raw text is preserved. Pass no_optimize:true to skip. Writes are deduped by default: (1) SHA-256 of trim(content) short-circuits byte-identical writes with { id, exact_duplicate:true } for free (no embed call); (2) failing that, semantic dedup returns { id, deduped:true, matched_score } when cosine ≥ 0.85. Pass force:true to bypass both, or use memory_supersede to explicitly correct a prior memory.

  Connector