"How to run code using Claude Desktop" matching MCP tools:

• security_deep_diveA

  Moltline Code ReviewA

  Run an OWASP-oriented security pass over a source file. PREMIUM (license). Checks injection sinks, auth/session handling, crypto misuse, SSRF/deserialization, and unsafe file/path handling — each finding cites the line, the OWASP risk class, and a concrete fix direction. Typical input {"code": "<file contents>"} returns {"issues": N, "findings": [{"line": N, "class": "A03 Injection", "fix": "...", "code": "..."}], "owasp_note": "..."}. Use on one source file when vulnerabilities are the question. Not for style or structure (complexity_report), and never a substitute for a security professional on high-risk code. Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": "<what is wrong and how to fix it>"}. Every call is read-only and idempotent, so after correcting the input it is always safe to retry.

  ConnectorNo auth

• declare_run_expectationsA

  LastPingA

  Commit, at the START of a run, to the criteria by which THAT RUN will be judged when it closes — before you can see how it turns out. This is how a run stops grading itself: once declared, a success ping whose body does not satisfy every declared criterion is recorded as a FAILED run with cause 'assertion', regardless of the exit code or what the ping claims. Call this right after your run's /start ping, before doing any work — see the assertions argument for the full, immutable contract, and get_ping_instructions' expectations_how_to for a worked example.

  Connector

  Destructive

  No auth

• list_skillsA

  civilquantsA

  List the 10 senior-QS skill methodologies CivilQuants exposes (tender review, risk assessment, QS measurement/contract advice, geotechnical + geo-environmental interpretation, earthworks, preliminaries, pavement design, subcontract analysis). Universal discovery — both tiers see the full list. Returns each skill's slug, title, one-line summary and tier; then call get_skill(skill=<slug>) to fetch the methodology body. The skills are paid-tier; a free caller gets a sign-up prompt from get_skill. NOTE: the document-heavy skills (tender review, the interpretation skills) need a code-execution client (Claude Code / Codex / VS Code) plus the chunking pack from get_document_pipeline to run a real tender pack — on a chat connector you can read the methodology but cannot chunk/parse files.

  ConnectorNo auth

• server.describeA

  Agent402.Tools: pay-per-call web toolsA

  [free] Describe this connector: flagship-first tools layer (search/answer as the front door), how to install (Claude Code / Cursor / npm), free vs paid tiers, and discovery URLs. Call this first.

  ConnectorNo auth

• spawn-ori-evalA

  OpenRouterA

  Get the instructions for running a model eval with Ori, then follow them. Ori runs the user's own agent on their own prompts, on a pinned harness and model, and grades what it did — so a score change means the model changed, not the environment. Call this tool FIRST, before writing any eval code: it returns a step-by-step recipe (install and auth checks, how to spawn `ori code -p`, how to relay Ori's scoping questions to the user, how to report results) that you carry out yourself. Do not hand-roll an eval instead. Use it when the user asks which model they should use, wants to compare or bake off models, wants to measure whether their agent or prompt does the right thing, wants to catch regressions in agent behavior, or asks how good their current model is. Works for any codebase in any language. Do not use it for plain unit tests that involve no model, and do not use it to re-run an eval that already exists (run `ori eval <file>` directly instead). Takes no arguments; the same document is published at https://openrouter.ai/skills/spawn-ori-eval.

  ConnectorOAuth

• prepare_consult_domain_expertA

  TasteA

  Get a humantaste.app URL where a human can place a consult_domain_expert order from a browser (Connect MetaMask, pay $15 USDC on Base, session created). Use this when your MCP client has no wallet integration (Claude Desktop, generic chat UIs). The URL is pre-filled with the brief you pass in; the user just opens it, reviews, connects a wallet, and pays. Returns the payment URL and the price. Free.

  ConnectorNo auth

• generate_walletA

  Blueprint Agentic Staking (Solentic)A

  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.

  ConnectorNo auth

• upload_fileA

  CluesoA

  Upload one or more files to Clueso. Three modes — pick by client + where the file lives: 1. **file_name** — HOSTED upload, the default for any non-UI / programmatic upload (Claude Code, Cursor, Claude Desktop, scripts). Returns an upload URL on Clueso's OWN base domain + a ready-to-run curl that streams a single local file to it; Clueso relays the bytes to storage server-side. The PUT targets the base domain — NOT cloud storage directly — so it works on desktop/agent clients that can't reach or are blocked from S3. Requirement: the client must be able to PUT bytes to the Clueso base domain (run the returned curl, or any HTTP PUT). The agent (or the user at a shell prompt) runs the curl. Prefer this whenever there's no human at a browser. 2. **file_url**: Pass a public https URL. Server fetches and stages the file. Returns mcp_upload_id immediately. Use when the file is already on the open web — no user interaction needed. 3. **request_hosted_upload** (UI mode — use ONLY when a human should pick files in a browser: many files at once, or a host with no shell / no PUT capability): Returns a single upload_token + upload_page URL. Share the link with the user; they open it in a new browser tab, drop their files, click Done. Then call check_uploads(upload_token) to retrieve all mcp_upload_ids. Call once for all files. Hosted uploads cover any number of files per call: one call issues one upload_token, and that token covers every file the user drops on the page. Repeat calls issue additional tokens, each tracking only its own files. The returned mcp_upload_id (prefixed `mup_`) can be passed to: - add_elements / update_elements (image or video → an element ON a clip: pass it as `type_data.mcp_upload_id`, on either tool — this is how a local image becomes on-canvas content, and how an existing element's source is swapped). To fill an animation's image slot, pass it inside `type_data.parameter_values` on update_elements only — parameter_values is an update-path field and is stripped on add. - add_audio (audio → project music track that plays under all clips) - add_clips(kind='video') (video or audio → sequential clip with auto-transcription) - add_clips(kind='pptx') (.ppt/.pptx → slide clips) - add_article_media (image/GIF → article asset) - analyze_audio (audio → transcript / silences / beats / features)

  ConnectorNo auth

• misakanet_submit_intakeA

  MisakaNetA

  [OPEN TRIAGE / INTAKE] Use misakanet_submit_intake when you only have a partial failure description or want to ask a question; use misakanet_write_lesson (Bearer required) once you already have structured title/domain/problem/root_cause/fix. submit_intake is open, rate-limited, no Bearer — output is a GitHub issue (intake,mcp-intake,pending-review) for maintainer triage, NOT a merged lesson. Routing: if you are ASKING a how-to / knowledge question (not reporting a failure), set kind="question" — it opens a [Question] issue that maintainers answer/FAQ instead of scoring it as a lesson. If kind is omitted, the server auto-detects question-shaped content (no error/fix/verification + question phrasing). Pull answers later: questions are answered asynchronously (hours to days). Re-call this tool with the SAME problem text later — the dedup response returns the maintainer's answer once it exists ({answered:true, answer}); or re-run misakanet_search on the topic for FAQ hits. Returns: object {submitted: boolean, intake_id, status, redactions_applied, quality_score, receipt, routing:{kind, auto_detected}, follow_up?}; duplicates: {submitted: false, duplicate: true, previous_issue} or {answered: true, answer} for answered questions. Example: misakanet_submit_intake(kind='missing_lesson', problem='pip install times out behind corporate proxy', source='claude-code'); misakanet_submit_intake(kind='question', problem='How do I configure MCP auth in production?', source='claude-code')

  ConnectorNo auth

• get_download_urlA

  BotverseA

  Get a presigned HTTPS URL to download the completed output file. Call after get_job_status returns 'complete'. URL expires in 24 hours. NOTE: fetching this URL is a direct S3 download, which is BLOCKED in sandboxed agent environments (claude.ai, Claude Desktop, Cursor). If you are in a sandbox, use get_output_content instead to receive the bytes inline over the tool channel.

  ConnectorNo auth

• executeA

  mcpA

  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 {}.

  ConnectorOAuth

• mcp_capabilitiesA

  FXMacroDataA

  Explain what the FXMacroData MCP server can do, which tools render MCP Apps, which tools return plain rows, what is public versus subscriber-only, and how to choose tools across ChatGPT, Claude, Cursor, Codex, and plain MCP clients. Use this when a user asks what is available, why visuals are not showing, or how to get the same result in a different interface.

  ConnectorNo auth

• get_page_performanceA

  rankparse-mcpA

  Google PageSpeed Insights report for a URL: Lighthouse performance/accessibility/SEO scores and Core Web Vitals (LCP, CLS, INP, FCP, TTFB), with lab and field (CrUX) data. Defaults to mobile; pass strategy=desktop for the desktop profile. Subject to a per-user daily cap (50/day) and a service-wide daily cap; successful responses are cached for 24h.

  ConnectorNo auth

• install_snippetsA

  Prism — Data Enrichment for AI AgentsA

  Return ready-to-paste configuration snippets for installing this MCP server in Claude Code, Cursor, Cline, Continue.dev, Windsurf, and Zed. Free.

  ConnectorNo auth

• get_iban_formatA

  ibanchecker-mcpA

  Return the IBAN format specification for a country, covering 90 supported IBAN-using countries. Returns JSON describing the country's total IBAN length, the BBAN layout (bank code, branch code, and account number positions and lengths), an example IBAN, and the SEPA-membership flag. Use this to understand or display how a country's IBAN is structured, to build input masks, or to explain a validation failure, not to validate a specific number (use `validate_iban` for that). An unsupported or unknown country code returns an error result describing the problem.

  ConnectorNo auth

• list_runtimesA

  MCPExplorerA

  List the runtimes generate_runtime_config supports (Claude Desktop, Cursor, VS Code, agent frameworks, …), with each one's config path. Enumerate these instead of guessing runtime slugs.

  ConnectorNo auth

• create_attention_directiveA

  freedom-mcpA

  Queue a short instruction for an external agent session — a coding/builder host (Grok terminal, Claude Code) or a Grok Bot desktop chat agent (host grok-bot, e.g. "send this to my FOS Integrator"). Does NOT type into their UI — the session must poll FreedomOS (poll-fo-directives.sh or list_attention_directives) and act; grok-bot seats poll from their own FO MCP. Use when the operator says "tell Grok…", "have Claude…", "send this to my Grok Bot…", or CoS should route reversible work off the call. Pass the same target_session_id the host polls (e.g. grok-<id>, claude-<id>, grok-bot-<agent-slug>). [write-tier — first use may require a manager's approval; a from-now-on approval makes future calls seamless, a just-once approval re-asks next time.]

  ConnectorNo auth

• amtrak_station_infoA

  AmtrakA

  Amtrak station lookup by code or name — station name, 3-letter code, city/state, street address, timezone, coordinates, and how many trains are currently inbound. "Where is the Amtrak station in Denver?", "what is station code NYP". Example: amtrak_station_info({ station: "Denver" })

  ConnectorNo auth

• list_lotteriesA

  Quick Lotto lottery resultsA

  List every lottery this site publishes results for, with the size of each draw machine (how many numbers are picked, and from how many). Call this first if you are unsure which lotteries are covered or what code to use.

  ConnectorNo auth

• get_mcpA

  Lulu Registry MCPA

  Full details for one MCP server from the unified index, by slug (as returned by search_mcps): description, per-client install commands (Claude Code / Claude.ai / JSON config), transports, categories, the registries it's listed on with links, and its trust score. Use after search_mcps when the user wants to install or inspect a specific server.

  ConnectorNo auth

• test_grammarA

  tabnasA

  Run TSV fixture content against a grammar in a fresh instance, using the fleet fixture convention (@tabnas/support): line 1 is a header, the input column is escape-decoded, the expected column is JSON or ERROR / ERROR:<code>. Returns {pass, fail, rows:[{row,input,expected,got,ok}]}. Refuses more than 10000 rows.

  ConnectorNo auth