Browse agents

Metabase integration: natural-language data analysis, dashboard management, SQL queries and automated insights, with SQL guardrails and audit logging.

Brazilian public data via BrasilAPI: companies (CNPJ), addresses (CEP), banks (BACEN) and national holidays.

Search and enrich company data: lookup by name, VAT or ID, NACE sector search, and financial data from official EU business registries.

Manage Apache Airflow via its REST API: list DAGs, inspect runs and task instances, trigger runs, and check failed DAGs and scheduler health.

Business intelligence: company and contact discovery, verification, enrichment, business signals, lists and governed delivery.

Pay-per-query x402 datasets: NPI healthcare, SEC filings, OFAC sanctions, crypto whales, Polymarket signals, patents and economic indicators.

US government records (short-term rental permits, lodging licenses, property violations, healthcare exclusions, EPA ECHO) and Norwegian company data.

Data quality checks on DuckDB, BigQuery, Athena, Databricks and Postgres, with LLM root-cause analysis of failures and proposed SQL remediations.

Local-first data quality workbench for Excel/CSV: validate against schemas and 10 zero-code constraint types (uniqueness, ranges, foreign keys, allowed values and more), with row-level error reports. Also ships a visual desktop app, CLI and REST API.

Query Snowflake, Google BigQuery and Databricks data products in natural language through Alkemi.

Search and query public datasets from the World Bank, IMF, Eurostat, OECD and WHO, and publish charts.

Query Swedish public data through Apiverket, including company data, SCB statistics, weather, transport and more.

Method CRM API integration: manage tables, files, users, events and API keys, with rate limiting and retries.

Kafka Schema Registry management across multiple registries, including schema migration.

Apache Superset: dashboards, charts, datasets, SQL Lab, security (users, roles, RLS, groups) and permissions audit, with built-in safety validations.

Brazilian agricultural data: prices, crop estimates, climate and deforestation from public sources including CEPEA, CONAB, IBGE, INPE and B3.

Query, create and update opportunities and contacts in VTENext, an open-source vtiger-based CRM, via its WebService API.

Search MercadoLibre products, get item details, browse categories, track trends and convert currencies across Latin America.

Datanika, the open-source ELT and dbt platform: browse connections, preview data, run dbt transforms, monitor runs and manage pipelines. Read-only by default.

dbt integration: dbt Core and Cloud CLI, project metadata discovery, model information and semantic layer queries.

Search French building permits (Sitadel open data), cross-referenced with DVF transactions, PLU zoning and BRGM natural and technological risks.

Turn business documents (PDFs, invoices, contracts, payroll) into structured datasets with classification, field extraction, PII masking and quality scoring.

Interact with Flowcore to perform actions, ingest data, and analyze and cross-reference data in your own or public data cores.

Power BI refresh with table-level polling and retry, refresh diagnostics, DAX queries with RLS simulation, PBIP source locating and refresh reports.

Operational ontology reference implementation: tools generated from a typed business domain model, with rule-checked, audited writes to systems of record.

Open data for La Réunion (French overseas region) from data.gouv.fr and the regional portal: economy, demographics, transport, health, education and more.

Greenhouse-gas emission factors and carbon calculations (activity, embodied EN 15978, PCAF financed emissions) with source references and data versions.

Run SQL queries, list jobs and get job status via the Databricks API.

Query Qlik Cloud apps and sheets and extract data from visualizations, with authentication and rate-limiting support.

Interact with the Keboola Connection data platform: list and access data from the Keboola Storage API.

dbt-core (OSS) project metadata, model and column-level lineage, and dbt documentation.

China apparel supply chain data: verified suppliers, lab-tested fabrics and industrial clusters, with AATCC, ISO and GB lab-test verification.

Query Power BI semantic models: browse workspaces, tables and measures, run DAX queries and page large results via local CSV.

Fine-grained sentiment analysis, keyword extraction and batch processing.

Deterministic, lexicon-based semantic word encoding and valence analysis: word-to-code mapping, semantic similarity and synonym/antonym lookup.

Automate or monitor business operations: sales recording, POS software and CRM.

Trust checks for Malaysian public datasets: freshness, licence, provenance and drift, with signed evidence and an offline-verifiable attestation chain.

POS and sales analytics for AirREGI, Smaregi and BASE e-commerce: store management, sales data queries, AI chat analysis and weather correlation.

Read-only BI pipeline governance: each table's stage from source to Power BI, what blocks the next stage, static SQL/TMDL/PBIR checks and evidence packs.

Airflow REST API: list DAGs, runs and task instances, tail logs and roll up DAG health. Read-only by default; trigger and clear are write-gated.

Capsule CRM: contacts, opportunities, projects, tasks, timeline activity, filters, workflow tracks and file attachments, with an optional read-only mode.

World data from primary sources via the Sugra API: markets, macroeconomics, company fundamentals, government, news, climate, maritime and entity screening.

Swiss open data: transport, weather, geodata, companies, parliament and more.

Databricks Genie API: ask natural language questions, run SQL queries and interact with Databricks conversational agents.

USDA FoodData Central nutrition data, paid per call via x402 (USDC on Base): food search, details, comparisons and recipes.

Social network analysis of YouTube comments: influencer centrality ranking, Louvain community detection and sentiment analysis.

Deterministic symbol oracle over a locally built index of the repo: whether a symbol exists, what a file declares, and what changed structurally since the last snapshot. Ships with a PreToolUse guard that stops an Edit/Write referencing a function, constant or type the repo does not declare, before the write lands. No LLM, no API keys, no network — the same code produces the same answer. Parsers for Go, Python, JS/TS, Rust, Ruby and shell. `bash install.sh`

Profiles how you use any MCP server into a reusable, read-only skill: workflows, call chains and each tool's safety class.

Maps a .NET Reqnroll/SpecFlow test-automation solution into a queryable SQLite file to search step definitions, check change impact and avoid duplicate code.

On-premise private AI systems from ARADIA on NVIDIA DGX hardware: hardware sizing, ROI modeling, partner onboarding, procurement and order tracking.

Reads local Claude Code, Codex and OpenCode usage logs: token totals, daily and hourly activity, per-agent and per-model breakdowns and a year-in-review recap.

Checks source-context freshness against a Git working tree and retrieves source-linked code relationships to surface stale knowledge and cross-file impact.

Explains known developer errors offline and deterministically (CORS, ESM/CommonJS, npm ERESOLVE, Next.js build, Postgres connection and DATABASE_URL errors): cause, ranked fixes and the documentation link. One tool, no LLM, no network.

AST-based code outliner, log compressor and context budget analyzer to reduce LLM token usage.

Health checks, binary validation and JSON auto-repair for MCP client configuration files.

AST-based dependency analyzer: flags unused packages, calculates actual install sizes and detects unmaintained dependencies.

Search and fetch animated, shadcn-compatible React components, design systems and templates, with install commands, from the aicanvas registry.

Browse and search Hyperiux Vault React/Next.js animation and interaction effects, with dependencies, changelogs, install commands and source code.

Versioned projects from assistant-built work: shareable HTML previews, version comparison, delegated approvals, artifacts, work assignments and source export.

Free ASO Score (Agent Signal Optimization) scanner scoring discovery, identity, trust, commerce, reputation, and memory signals, with maturity levels, evidence, and prioritized fix plans. Local stdio, no API key required. `npx -y @forgemeshlabs/aso-score-mcp`

Prevents double charges and duplicate side effects from agent tool calls: concurrent races elect one winner, late duplicates replay a sealed receipt.

Demand-signal scanner for validating product and dev-tool ideas using GitHub repo signals, Hacker News attention and npm/PyPI download counts.

Tailwind CSS palettes (50–950) from any color for Tailwind v4, v3, v2 and v1, computed in OKLCH, plus the closest Tailwind color to any color. Run it with `npx tailwindshades-mcp` or use the hosted endpoint.

Local-first runtime for coding agents: bounded workspace access, guarded writes, AST search, LSP navigation and diagnostics, and Git tooling.

Deterministic execution guardrails, isolated AST-based math evaluation, SSRF-safe DNS routing and malformed JSON repair.

Records Python, Rust and TypeScript program runs to local SQLite so coding agents can query call trees, exceptions and value flow.

Check whether an LLM model ID is deprecated, retiring or retired, and what to migrate to, across OpenAI, Anthropic, Azure, Bedrock, Google and Cohere.

Read-only debugging for Hono apps: recent exceptions with their requests, logs and queries, requests filtered by status or duration, and the slowest queries.

Read-only access to the agentic-os governance, SDLC and QE methodology, with install planning and verification.

Self-hosted live library docs, code audits with file:line findings, BM25-ranked snippets and lockfile-aware version pinning.

Semantic file and code search by description, with local indexes, AST-aware chunking, optional reranking and API-based or fully offline embedding models.

Design review of rendered UI for coding agents: submit a preview URL, get findings with element references and recheck after fixing. Read-only.

Checks if a project idea already exists on GitHub, npm or Python repositories and suggests maintained alternatives to extend instead of scaffolding anew.

Hallucination guard: verify a claim against evidence (supported, refuted or not enough evidence) with a confidence score and abstain flag.

Dependency-upgrade impact analysis for Python and .NET: which API usages break, with line numbers and fix hints, plus detection of hallucinated API calls.

Reduced-motion and WCAG 2.2.2/2.3.3 verification for web animation: validate animation specs and compile them into reduced-motion-safe CSS.

DAP-to-MCP bridge for native debugging via CodeLLDB: stack frames, registers, locals, disassembly, memory, crash dumps and crash fix/verify workflows.

Checks coding-agent context files (CLAUDE.md, AGENTS.md, SKILL.md) against the git index: broken links, missing paths, undefined commands and drift.

Search, inspect and install Ballmac UI React + Tailwind components, blocks and templates, with props, keyboard notes and the exact shadcn install command, and plan whole pages from blocks.

Merge gate for AI-written code: catches placeholder code, unfailable tests, unsupported completion claims and nonexistent API calls, then returns a fix plan.

Host-level telemetry gateway letting sandboxed agents fetch container logs and track kernel resource metrics.

Local stdio bridge to the hosted Delx Protocol MCP endpoint, with client install, doctor checks and live tool discovery.

Contract-first programming language: check types, effects, capabilities and contracts in agent-written modules and review changes for new authority.

Generate PDFs from HTML, a URL or a template with JSON data, and extract text or Markdown from PDFs.

Query problems, logs, events, SLOs, security insights and performance metrics from self-hosted Dynatrace Managed environments.

Lint HTML email with Emailens: rendering issues in Gmail, Outlook, Apple Mail and more, per-client CSS compatibility scores, dark mode simulation and fixes.

Build and maintain Altium Designer component libraries: read and write .PcbLib footprints and .SchLib symbols, with IPC-7351B footprints and STEP models.

Audits website and API agent readiness: robots.txt AI rules, llms.txt, agent cards, MCP server cards and OAuth metadata, with maturity scores and fix plans.

Local CI/CD for agents: runs jobs on LGH git events in isolated checkouts, with failure diagnosis, approval gates, auto-rollback and a web console.

Duplicate code detection with jscpd: check snippets and files for copy/paste duplication against a scanned project before committing.

Local launch-readiness audit for AI-built apps: read-only checks, an evidence-based 0-100 score and guided fixes.

Test management: author manual test cases, run executions, cut releases and link automated tests, with prompts for flaky-test triage and release readiness.

Breaking-change diffs for npm packages, so coding agents avoid writing code against outdated APIs.

Reusable prompt templates with multi-step chains, quality gates and reasoning frameworks, exportable as native skills for coding agents.

Control Claude Managed Agents: launch agents, watch their events, reply, approve tool calls and stop them.

Nahook webhook platform: trigger webhooks, inspect deliveries, retry failures and manage endpoints.

Developer toolkit: semantic code search, natural-language database queries, docs indexing and OpenAPI introspection.

Index TypeScript/React repos into a code graph: who-renders and who-calls queries, blast radius, dependency cycles, dead code and symbol signatures.

Voice interface for Claude Code: live speech-to-text with turn-taking, spoken replies with xAI Grok voices, per-subagent voice personas and a real-time HUD.

Monitors coding-agent token cache using inventory theory (EOQ) and signals optimal session restart timing via a live dashboard and terminal status line.