Browse agents

Provides TypeScript API information so agents can work with APIs not in their training data.

Subscription-aware LLM router for Claude Code: routes tasks to providers like OpenAI, Gemini, Groq and Ollama by complexity, subscription usage and cost.

Local Python/TypeScript code graph: call tracing, multi-hop impact analysis, authz reachability audits, coupling metrics and architectural drift detection.

Converts OpenAPI/Swagger specifications to MCP format so AI assistants can call REST APIs.

Fetch JSON, text and HTML data.

Manage App Store Connect apps, builds, TestFlight, subscriptions, reviews and more via its API.

Lets your coding agent ship a SwiftUI iOS subscription app from idea to TestFlight: niche validation with live App Store data, SwiftUI scaffold, Supabase backend, App Store Connect subscriptions and RevenueCat, localization, ASO, screenshots. Gated stages, human approval for irreversible actions, every service optional.

Connect to ZenML MLOps and LLMOps pipelines.

Android automation tool suite for developer workflows and testing.

Offline Garmin Connect IQ SDK documentation with search and API examples.

UploadKit's React upload components, Next.js route handler scaffolds, bring-your-own-storage setup (S3, R2, GCS, B2) and full-text docs search.

Turns npm or PyPI lockfile diffs into upgrade plans with semver classification, breaking changes, fixed CVEs, migration links and risk-ranked recommendations.

Developer utilities: Base64 and URL encoding, JWT decoding, DNS lookup, UUID generation, JSON formatting, User-Agent parsing and IP lookup.

API testing tool with YAML tests and structured JSON failures agents can act on: run, validate, inspect, rerun failed tests and get fix plans.

Perfetto trace analysis: run PerfettoSQL queries on trace files, with Chrome tools for page loads, scroll jank, main-thread hotspots and stdlib discovery.

Query Jaeger distributed tracing: list services and operations, search and fetch traces, and view service dependencies.

C++26 paper reference backing a Claude Code plugin: paper lookup, fuzzy search and compiler support status over the ISO/IEC 14882:2026 corpus.

Structural memory for coding agents: indexes TypeScript/JavaScript repos for callers, callees, symbol locations and branch-aware blast-radius impact.

Semantic code graph: indexes a codebase into a typed graph for call-chain tracing, data-flow analysis, semantic search and invariant checking.

Offline calculator that evaluates expressions in fixed-point, IEEE-754 double or exact rational arithmetic, labelling each answer exact or inexact.

Create and manage public HTTP, TCP and UDP tunnels to local services with custom subdomains, regions and load-balanced pools, managed cloud or self-hosted.

Routes code search through language-server indexes (clangd, Roslyn, tsserver, pyright) instead of grep, plus symbol-level edits and git/p4 output compaction.

Shorten links, read click analytics, generate branded QR codes and manage links on opn.onl, the open-source, self-hostable URL shortener.

Audit a domain's email deliverability (SPF, DKIM, DMARC, MX, blacklists, catch-all, domain age) and get a health score via an Apify actor.

Webhook callbacks for AI agents: create callback URLs, wait for signature-verified webhooks instead of polling, verify HMAC and list or replay callbacks.

Structural code context via TypeScript AST analysis: compressed symbol indexes, dependency graphs and git diffs, without a vector database or embeddings.

Headless rendering and verification of native Rust GUIs: accessibility tree, semantic selectors, contrast and focus-order checks, and screenshot diffs.

CI for ink interactive-fiction stories: compiles, playtests every branch and finds runtime errors, unreachable knots and every distinct ending.

Semantic codebase search and persistent working memory: hybrid dense and BM25 search over AST-aware chunks, a symbol graph and notes that survive restarts.

Leaderboard ranking AI coding operators by token efficiency, with signed submissions, diagnostics and simulations; only token counts leave the machine.

Audit images on a web page via the imagedimensions.com API: natural vs rendered dimensions, oversized-image detection and format breakdown.

Log tools for on-call and SRE workflows over rlg (RustLogs) files: tail events by level or target, filter with JSON-path predicates and summarize errors.

Async execution for agent tool calls: payload schema checks, retries and circuit breakers, idempotency keys, approval gates, replay and signed-webhook results.

Checks agent-written code against the repo's git-history patterns, flagging foreign dependencies, reinvented functions, misplaced code and gamed tests.

Affected-test selection for Kotlin/Android projects: finds the unit tests impacted by working-tree changes via function-level static analysis.

Scaffold and upgrade multi-language projects with the create-packkit generators, and compose a frontend and backend into one fullstack repo.

Local retrieval over ISTQB, OWASP, IEEE, ISO and EU AI Act QA standards, plus QA effort estimation, QA document review and JUnit/CSV flakiness analysis.

Search the quelllm.fr open-weights LLM catalog: compare models by parameters, VRAM per quantization, speed and license, and estimate VRAM and costs.

Search @imqueue docs, scaffold typed services and clients, access the CLI and manage your service fleet.

Accessibility scanning with axe-core (WCAG 2.1 AA, EN 301 549, PDF/UA) via wcagc: scan URLs and PDFs, crawl sites, replay journeys and read violation trends.

Deterministic guardrail for AI-written diffs: AST-based checks for SQLi, SSRF, XXE, hardcoded secrets and over-abstraction, scoped to the changed lines.

Read-only introspection of Symfony codebases: routes, controllers, services, entities, schema, migrations, Doctrine, Messenger, Twig and API Platform.

Generate realistic, schema-conformant JSON test data (single documents or relational batches) from reusable templates via the JsonFabrica API.

Public HTTPS links for local files, directories or dev servers, via a live tunnel or published copy, with password protection, TTLs and named subdomains.

Pin visual feedback on live web pages with the Yocoolab extension and hand it to coding agents with the element, selector and screenshot attached.

Read-only per-function CRAP scores (complexity and coverage) that point to the worst function to fix next, with uncovered lines and near-duplicates.

Query UniFi API docs (Network, Protect, Site Manager and more): endpoint search, field-level schemas and code examples. Docs only, no controller access.

Turn Markdown into a shareable link rendered as a typeset document (tables, Mermaid, math, pagination); content is stored in the URL, not uploaded.

Create live webhook endpoints and read back the deliveries they receive; endpoints keep working after the session ends.

Policy layer for multi-agent workspaces: a JSON file sets what each path is worth, agents dry-run cleanup plans, and actions land in a hash-chained journal.

Read, write, analyze and test VBA in Excel, Word, PowerPoint and Access files, with static analysis; the file layer works without Office installed.

Autonomous coding pipeline: a frontier model plans and reviews, a local model implements under TDD, and a merge gate re-runs the suite on the rebased branch.

Read, search, create, update and delete gists on your own [Opengist](https://github.com/thomiceli/opengist) instance — the self-hosted pastebin powered by Git. File contents and revisions, commit history, forks and likes. Bounded results, untrusted-content markers, and a server-issued confirmation token on everything that deletes or publishes. `npx -y opengist-mcp`

Yandex Delivery B2B API: express-courier claims (price check, create, track, cancel) and pickup-point/NDD orders.

Yango Delivery B2B API (international Yandex Delivery): express-courier price checks, delivery claims, courier tracking and confirmation codes.

Unofficial DoorDash Delivery integration.

Greater China local services: Meituan/Ele.me delivery, Didi ride-hailing, WeChat Pay/Alipay, Amap/Baidu Maps, 12306 rail and Taobao/JD shopping.

Book, label, track and cancel Royal Mail and Parcelforce shipments across UK and international services.

Order food and groceries on DoorDash via its CLI (macOS arm64): search stores, compare fee-included totals, build carts; orders need user approval.

Compare parcel and letter delivery prices across carriers in 27 European countries.

Live USPS, UPS, FedEx and DHL rates for parcels shipped from the US, from a plain item description, plus checkout links, checkout status and tracking.

Book LTL, FTL, van and box-truck freight through the Warp network, with in-chat login, Stripe-charged bookings and carrier dispatch.

Unofficial Yandex Lavka (Russia) grocery ordering: search the catalog, build a cart and place orders with two-step confirmation before any charge.

MCP proxy that replaces oversized tool results with a preview and an on-demand handle to save tokens.

Discover ReactUse React Hooks: signatures, demos and usage patterns from the library docs.

Local codebase architecture analysis: tech-stack overview, internal dependency graph with cycle detection, risk hotspots and module summaries.

Build, sign and publish iOS and Android apps via Codemagic CI/CD, App Store Connect and Google Play.

Let non-technical users request UI changes on your live site, then pull each request with its element and page into your coding agent to open a PR.

Probe live APIs and classify why each endpoint failed, with root cause, evidence and confidence. Supports FastAPI, Express, Next.js, tRPC and GraphQL.

Local-first backend dev workspace: API debugging, SSH, database and diagnostics tools, with scoped safety policies and confirmation for risky actions.

Drive the local ProxyKit MITM debugging proxy: inspect HTTP(S), gRPC and WebSocket traffic, create mocks and rewrites, replay requests and run chaos scenarios.

Fast, local, non-autoregressive System-1 decision engine as MCP tools — typed decisions (classify / score / yes-no) over text, email, tickets or JSON in 100+ languages, with calibrated confidence and no text generation, so nothing to hallucinate. Offloads routing/triage/gating judgment calls from the main model; runs on-device, offline by default. `pipx install mcp-laya`

Deterministic multi-criteria decision analysis: rank options on weighted criteria via weighted-sum, weighted-product or TOPSIS, with sensitivity analysis.

Math engine combining SymPy, NumPy and Matplotlib for symbolic algebra, numerical computing and data visualization.

Numerical methods: root finding, numerical integration, differential equations (RK4) and Lagrange interpolation.

Math tools for agents: theorem search, PSLQ constant identification, OEIS lookup, Lean kernel checks and applicability checklists.

Connect to Kaggle to download and analyze datasets.

Offline tabular data access: describe, preview and query CSV, TSV, JSON, Parquet and Excel files, diff datasets and build an interactive HTML explorer.

Mathematical computations: basic arithmetic, advanced functions, statistical analysis, unit conversions and financial calculations.

Create, read, validate and save Stella system dynamics models (.stmx files in XMILE format) for scientific simulation and modeling.

Graph analysis with NetworkX: centrality algorithms, community detection, PageRank and graph visualization.

Compare approximate filter data structures: Bloom, Counting Bloom, Cuckoo and SuRF.

Forecasting and prediction with Chronulus AI agents.

Educational server for math operations, statistics, visualization and persistent workspaces.

Real-time LLM and VLM comparison with benchmarks, prices and personalized recommendations from multiple data sources.

Data quality evaluation with Dingo: run rule-based and LLM-based evaluations and list its rules and prompts.

Transparent statistical analysis with cited findings, integrity-hashed result bundles and a calibration corpus of measured detector false-fire rates.

Create and interact with GrowthBook feature flags and experiments.

Physics-based anomaly detection with Klein-Gordon wave equations: scans, fingerprinting, token risk, wallet profiling and price manipulation detection.

Profile local tabular files (CSV, TSV, Parquet, Excel, JSON): dataset overview, per-column statistics, data-quality audits and dtype suggestions.

Local deterministic calculations: exact-precision math, date arithmetic, unit conversion, statistics, subnet math, haversine and Levenshtein distance.

Create, manage and automate Label Studio projects, tasks and predictions for data labeling workflows.

Interact with and control Jupyter Notebooks.

QUBO/Ising optimization with classical, hybrid and quantum solvers, paid per call via x402 (USDC on Base).

Link multiple data sources (SQL, CSV, Parquet and more) and analyze the data for insights and visualizations.

Judgment calls on small, cheap models: yes/no, pick-one and rate questions about any text, answered YES, NO or UNSURE. Runs on TypeSafe's Jev, open models on Ollaya, Ollama or a local NLI model; `each` judges up to 1,000 texts per call.

Exploratory data analysis that finds feature interactions and subgroup effects, with p-values, effect sizes and literature citations.

Deterministic date, math and unit tools: time snapshots, calendar math with natural-language parsing, expression evaluation and Pint-based unit conversion.

Create validated, maintainable data charts and dashboards with Vizro tools and templates.

Classical hypothesis testing, effect sizes, power and sample-size analysis and multiple-comparisons correction, returned as cited, assumption-checked answers.