lookupd

code-execution

5,846 MCP servers tagged code-execution, 1,428 up right now. Live servers first, then by uptime; never by payment.

  1. app.loutre/loutre up 0 agent searches in 30 days

    Creates and manages hosted mock HTTP APIs from OpenAPI, Swagger or TypeScript types, with configurable responses, latency and request logs.

  2. app.moosetracker/moose-tracker up 0 agent searches in 30 days

    Generates sound effects, songs and instrument samples as WAV, Ogg or Opus files, and converts songs to MIDI and tracker formats.

  3. app.netlify.shigoto-dogu/order-eval up 0 agent searches in 30 days

    Runs regression checks on Japanese order automations, fetching synthetic cases and scoring outputs against fixed answers with CI gate…

  4. app.nicetohave/kits up 0 agent searches in 30 days

    Searches, previews and downloads ready-made build kits with step-by-step recipes and fixes for Claude Code and Codex projects.

  5. app.openkrill/agent-trace up 0 agent searches in 30 days

    Analyzes a pasted AI agent tool-call log to flag failed, looping, repeated, or slow calls, and lets you send feedback to maintainers.

  6. app.openkrill/design-md up 0 agent searches in 30 days

    Lints and diffs DESIGN.md files with the Google linter, and generates a starter DESIGN.md from a public webpage's CSS.

  7. app.openkrill/live-card up 0 agent searches in 30 days

    Renders HTML cover and motion designs into Apple Live Photos, MP4 videos or GIFs, and tracks render job status.

  8. app.openkrill/market-indicators up 0 agent searches in 30 days

    Computes technical indicators like SMA, EMA, RSI, MACD and VWAP from user-supplied prices or a currency pair; also sends feedback.

  9. app.perfumate/perfumate up 0 agent searches in 30 days

    Lets an agent search perfumery materials, build and check IFRA-compliant formulas, and manage a user's shelf, batches and notes.

  10. app.showitworks/show-it-works up 0 agent searches in 30 days

    Records agent verification runs, uploads them, and manages shareable viewer links with expiry dates and task search.

  11. app.surewhynot.quantum-artificer/quantum-artificer up 0 agent searches in 30 days

    Runs scientific computations for agents: symbolic math, numerical solvers, ODE simulation, chemistry thermodynamics, and quantum circuit…

  12. app.ucad/ucad up 0 agent searches in 30 days

    Lets an agent script, build, view, and share 3D CAD models in a user's account, with reference examples and drawing inspection.

  13. art.allover/agentee up 0 agent searches in 30 days

    Lets an agent search and price cotton tees, manage a cart, apply promos, generate custom prints, and prepare checkout for the human to pay.

  14. buzz.limitless/mcp up 0 agent searches in 30 days

    Reads Solana token prices, portfolios and bonding-curve quotes, and builds unsigned buy/sell transactions for the caller to sign and submit.

  15. ca.bakhour/profitcollector up 0 agent searches in 30 days

    Offers pay-per-call DNS, TLS, security header, JWT, hashing, JSON and text utilities for developers and security checks.

  16. ca.criticalpathpartners/primavera-p6-forensic-scheduling up 0 agent searches in 30 days

    Runs forensic scheduling analyses on Primavera P6 XER files, including delay windows, DCMA-14 health checks, and Monte Carlo risk forecasts.

  17. ca.gpucloud/gpu-cloud up 0 agent searches in 30 days

    Rent GPU servers by the hour in Montréal, check live stock and prices, launch, manage and bill servers in CAD.

  18. cc.aiones/dev-toolbox up 0 agent searches in 30 days

    Offers developer utilities: Base64 encode/decode, UUID v4 generation, current time lookup, and JSON validation and formatting.

  19. cc.brickbank/brickbank up 0 agent searches in 30 days

    Runs paid, pre-built tool operations across many upstream services, with search, cost estimates, schema lookup and run status tracking.

  20. ch.kulalabs.pazair/pazair up 0 agent searches in 30 days

    Lets agents search, buy and sell services on a marketplace with pay-on-delivery, signed receipts, budgets and a community Q&A board.

  21. cloud.doner/hypnotic-patterns up 0 agent searches in 30 days

    Lets an agent browse and fetch Python lessons, quiz answers, and numpy/matplotlib pattern scripts for learning.

  22. cloud.redu/mcp up 0 agent searches in 30 days

    Lets an agent provision and manage EU-hosted VMs, databases, firewalls, and API keys, and run shell scripts on them.

  23. cn.com.bioinformatics/weishengxin up 0 agent searches in 30 days

    Lets an agent discover ~160 bioinformatics plotting modules, upload TSV or RDS data, submit background plot jobs, and poll results.

  24. cn.pianam/devtools-mcp up 0 agent searches in 30 days

    Provides offline developer utilities: timestamp and unit conversion, JSON format/validate, UUID and QR generation, plus npm and DNS lookups.

  25. cn.pianam/study-mcp up 0 agent searches in 30 days

    Balances chemical equations, computes molar masses, looks up elements, solves math and physics problems for study.

  26. co.betterchess/betterchess up 0 agent searches in 30 days

    Analyses chess positions with an engine, maps attacked squares and reviews finished games; one tool also returns in-page coaching code for…

  27. co.civai.nova/code-interpreter-agent up 0 agent searches in 30 days

    Runs shell commands and generates, executes, and debugs code through a remote interpreter for general coding tasks.

  28. co.civai.nova/terminal-command-agent up 0 agent searches in 30 days

    Runs bash, sh, or zsh commands on a remote cloud environment and replies conversationally when requests need clarification.

  29. codes.onv/onv-mcp up 0 agent searches in 30 days

    Runs quant strategy backtests, AI-generated strategy code, market data queries, and multi-exchange account and position reads.

  30. com.2duckserver/l2ducks up 0 agent searches in 30 days

    Lets an agent rent and control a live Lineage 2 game character to hunt, chat, trade and move around.

  31. com.99tests/mcp up 0 agent searches in 30 days

    Orders human-run real-device app tests, returns checkout links, job status, and verified bug findings as fix prompts.

  32. com.a2a2p/a2a2p up 0 agent searches in 30 days

    Lets agents turn physical part requirements into engineering reviews, beam section derivations, simulation studies, and pricing estimates.

  33. com.a2awire/benchmark-accept-1102-reclaim-342a471e up 0 agent searches in 30 days

    Lets agents list, start, and submit answers to scored benchmarks, read run results, and hire marketplace agents with escrowed USDC payments.

  34. com.a2awire/benchmark-access-change-request-recertify-2026-09-15-b578285f up 0 agent searches in 30 days

    Lets an agent start, submit answers to, and score benchmark runs, plus fetch corpora and results, on a testnet-funded marketplace.

  35. com.a2awire/benchmark-ap-exception-review-2026-09-10-run-037bea up 0 agent searches in 30 days

    Runs a benchmark of synthetic accounts-payable exception cases: lists tasks, starts scored runs, submits answers and reads results.

  36. com.a2awire/benchmark-ap-exception-review-2026-09-10-run-13e274 up 0 agent searches in 30 days

    Lets an agent run a benchmark on AP exception cases: fetch the corpus, start a scored run, submit answers, and read results.

  37. com.a2awire/benchmark-application-audit-2026-10-01-6e0ad047 up 0 agent searches in 30 days

    Runs a 12-case finance application audit benchmark, fetching corpus, submitting answers, and reading scores for exception review tasks.

  38. com.a2awire/benchmark-catch-the-overpayment-v1 up 0 agent searches in 30 days

    Offers a benchmark corpus, run scoring and a job board where agents can find paid work and hire other agents for tasks.

  39. com.a2awire/benchmark-coded-claim-audit-2026-09-14-a7b04acd up 0 agent searches in 30 days

    Benchmark tools for a synthetic healthcare claim audit: fetch corpus, start scored runs, submit answers, and read results.

  40. com.a2awire/benchmark-cw-capitals-1108-a17627f5 up 0 agent searches in 30 days

    Runs and scores benchmark tasks: list and fetch published benchmarks, start scored runs, submit answers, and read results.

  41. com.a2awire/benchmark-data-record-audit-2026-09-19-ec80e494 up 0 agent searches in 30 days

    Runs a data record audit benchmark: fetches case packets, submits answers, and reads scores for synthetic data exception cases.

  42. com.a2awire/benchmark-data-record-triage-2026-10-12-8effd564 up 0 agent searches in 30 days

    Lets an agent browse and compete in A2AWire benchmarks, fetch corpora, submit answers, and check scores and escrow payments.

  43. com.a2awire/benchmark-document-review-2026-10-02-6e5a2dd9 up 0 agent searches in 30 days

    Lets an agent list, start, and submit answers to document-review benchmarks, then read scores; runs in a testnet faucet environment.

  44. com.a2awire/benchmark-freight-bill-review-2026-09-14-6c5a409b up 0 agent searches in 30 days

    Lets an agent take part in a testnet benchmark: fetch corpus, start runs, submit answers to freight bill exception cases, and read scores.

  45. com.a2awire/benchmark-freight-bill-screen-2026-09-24-8d42472e up 0 agent searches in 30 days

    Lets an agent run freight bill exception benchmark cases, submit answers, and retrieve scores on a testnet accounts payable screen.

  46. com.a2awire/benchmark-freight-bill-validate-2026-09-17-5c17ece8 up 0 agent searches in 30 days

    Lets agents run a freight bill exception benchmark: fetch corpus and tasks, submit answers, and read scores. Also offers marketplace…

  47. com.a2awire/benchmark-invoice-reconcile-2026-09-23-9888f269 up 0 agent searches in 30 days

    Lets an agent start and submit scored invoice reconciliation benchmark runs covering duplicate and exception cases, with retrieval of…

  48. com.a2awire/benchmark-invoice-total-extraction-koda-24cece89 up 0 agent searches in 30 days

    Lets agents list and start paid-free benchmark runs, submit answers, and read scores for invoice total extraction tasks.

  49. com.a2awire/benchmark-medical-record-review-2026-09-21-dd8c58b7 up 0 agent searches in 30 days

    Lets an agent list, start, and submit answers to a free medical record review benchmark and check scores on its own runs.

  50. com.a2awire/benchmark-moderation-case-review-2026-09-19-ba3b90e4 up 0 agent searches in 30 days

    Runs moderation case review benchmarks: fetches corpus, starts scored runs, submits answers and reads results for trust and safety tasks.

Previous · Next (page 2 of 117)

All capabilities · Search instead