Agent superpowers — ranked tools, parsers, and services for Claude Code, Cursor, and OpenClaw agents

Ranked installable tools (PDF OCR, NFS-e invoice parsing, boleto extraction, bookkeeping), 71 Chrome-verified cloud services, and reproducible evals on real-world corpora — all queryable via one MCP server. Stop guessing. Start shipping.

Solve a task — installable tools, ranked by real-world evals

When your agent hits a capability gap — extract text from a Brazilian NFS-e invoice, OCR a scanned PDF, parse a boleto — the /solve/ pages rank candidate skills, MCPs, vendor APIs, and local binaries by reproducible field-level accuracy on real-world corpora. Not marketing blog posts. Not training-data vibes. Actual evals you can re-run.

CNPJ enrichment for Brazilian bookkeeping agents — what to install, ranked

Top pick: auxiliar-cnpj-fetch

Ranked CNPJ enrichment sources for AI agents doing Brazilian bookkeeping. After extracting CNPJs from NFS-e invoices, agents need to enrich each with razão social, CNAE, regime tributário (Simples Nacional + MEI flags), full address, and partners. Top pick: auxiliar-mcp's invoke_capability(tool='fetch_cnpj') — multi-provider cascade (BrasilAPI → CNPJ.ws), no token required for free anonymous tier, single auth surface for 220+ other Brazilian public-data tools.

Last verified 2026-04-29

NFS-e field extraction for agents — ranked by field accuracy on Brazilian São Paulo invoices

Top pick: auxiliar-nfs-e + Surya

Structured-field NFS-e parser for Brazilian agents. 100% field accuracy on São Paulo invoices when paired with Surya OCR (41/41 fields across 2-doc corpus). Also scored: Google Document AI (88%), Tesseract (63%). Outputs typed JSON with prestador, tomador, CNPJs, valor, ISS, código de serviço, and RPS.

Last verified 2026-04-23

PDF text extraction for Claude Code agents — what to install, ranked by accuracy

Top pick: surya

Ranked installable OCR tools for Claude Code / Cursor / Claude Desktop / OpenClaw agents parsing PDFs, Brazilian NFS-e invoices, boletos, and phone-photo receipts. Surya leads on word accuracy (76.9%) on a 10-document real-world corpus. Tesseract 5 runs 14× faster. Google Document AI wins on mobile-captured receipts.

Last verified 2026-04-21

Browse all /solve/ task rankings →

Install the MCP server — one install, twelve tools (v0.11.0)

One MCP, one query. find_capability ranks across every kind of indexed thing — cloud services, ClawHub skills, MCP servers, Claude Code plugins, parsers, public-data lookups, /solve/ task templates. Pass a query, a job-to-be-done tag, or both. 71 cloud services + 3 task rankings + skills/MCPs/plugins/parsers/data, all Chrome-verified or eval-scored on real-world corpora. Works with Claude Code, Claude Desktop, Cursor, OpenClaw.

claude mcp add auxiliar -- npx auxiliar-mcp

Unified Capability tools (preferred)

ToolWhat it does
find_capabilityRanked search across every Capability. Filter by query, jtbd, element_type, agent_context. Returns id, page_url, install command, eval score, jtbd tags.
get_capabilityFull record by stable slug — pricing tiers, risks, install spec, deps, eval records, distribution surfaces.
list_capabilitiesFiltered enumeration. element_type / category / jtbd / agent_context (AND semantics).
compare_capabilities2–5 ids → row-per-field aligned comparison. Same data backing as the /compare/ pages.

Legacy single-purpose tools (still wired; sunset in a future version)

ToolWhat it does
solve_taskPer-task ranked tool recommendations (PDF OCR, NFS-e extraction, …). Aliases: pdf, ocr, nfs-e, boleto, invoice-extraction, bookkeeping-ocr, receipt-parsing, document-ai.
list_solve_tasksDiscover every /solve/ ranking — top picks + categories + agent compatibility.
recommend_serviceCloud-service recommendation for a use case ("transactional email for Next.js", "edge-friendly DB")
get_pricingChrome-verified pricing tiers, free-tier limits, cost gotchas
get_risksKnown risks, vendor lock-in, recent breaking changes
check_compatibilityVerify a service works with your framework + runtime
setup_serviceStep-by-step integration: env vars, SDK setup, gotchas
list_servicesBrowse the 71-service catalog, filtered by category

71 services | 16 categories | 3 ranked tasks | Chrome-verified or eval-scored

npm: npmjs.com/package/auxiliar-mcp

Browse

🧭 /solve/ — ranked tools

PDF OCR, NFS-e parsing, bookkeeping extraction — with real-world evals

/skill/

ClawHub skills indexed with eval scores

/mcp/

MCP servers for AI agents

/plugin/

Claude Code plugins + agent-host extensions

/data/

Public-data lookups (BR Receita Federal, identifiers)

Email

Resend, Postmark, SendGrid, AWS SES

Auth

Clerk, Better Auth, Auth0, Firebase

Database

Neon, Supabase, Turso, PlanetScale, RDS

Payments

Stripe, Paddle, Polar, Lemon Squeezy

Search

Algolia, Typesense, Meilisearch, Postgres FTS

Deploy

Vercel, Railway, Render, Fly.io

Stacks

Pre-built combos: auth + DB + email

Migrate

Switch services without pain

Jobs

Post a project, get it delivered

How it works

  1. Agent hits a capability gap — "extract NFS-e fields from this PDF", "best email for Next.js", "OCR a scanned receipt"
  2. Queries auxiliar-mcp — find_capability ranks across every kind of indexed thing (cloud services, skills, MCPs, plugins, parsers, public-data); legacy solve_task + recommend_service stay wired for backward-compat
  3. Gets structured ranked data — scorecards with field accuracy / latency / cost, install commands, pricing, risks, alternatives considered + reason dropped
  4. Installs + integrates — using verified templates and copy-paste commands
  5. Reports back — outcome feeds the next agent's decision via the community feedback loop

Recently updated services

Algolia

Choose if: You need enterprise-grade hosted search with the best ecosystem, InstantSearch UI widgets, and sub-millisecond query times.

The most popular hosted search-as-a-service. Fastest query speeds, largest ecosystem with InstantSearch UI widgets, but pricing scales aggressively.

SOC 2SOC 3GDPRHIPAA (Enterprise)
HIGH Pricing is negotiable — always negotiate

Anthropic

Choose if: You need the best coding quality, long-context analysis, safety, and strongest privacy commitments.

Claude 4.5 and 4.6 models, strongest coding and analysis capabilities. Best safety and alignment practices. Strongest privacy commitments among frontier labs.

SOC 2GDPRHIPAA (Enterprise)

Auth.js

Choose if: You have an existing NextAuth v4 project you need to maintain — do NOT start new projects with Auth.js.

MAINTENANCE MODE: Auth.js team joined Better Auth in Sept 2025. v5 never left beta. Use Better Auth for new projects.

HIGH Maintenance mode HIGH No pre-built UI

Auth0

Choose if: You need enterprise compliance (HIPAA, FedRAMP, SAML, LDAP) and have the budget for it.

Enterprise-grade identity platform. Feature-rich but expensive — pricing has drifted upward since Okta acquisition in 2022.

SOC 2HIPAAGDPRFedRAMP
HIGH Pricing drift post-Okta acquisition HIGH Complex pricing model

AWS RDS

Choose if: You are already on AWS, need enterprise compliance, and have ops capacity to manage VPC and security group configuration.

Amazon's managed relational database. Battle-tested and feature-complete, but complex pricing with many hidden add-on costs.

SOC 2HIPAAGDPRFedRAMPPCI DSS
HIGH Free tier is only 12 months HIGH Multi-AZ doubles the cost

AWS S3

Choose if: You're already on AWS and need the full feature set — lifecycle policies, Glacier archival, event triggers, S3 Select, and compliance certifications.

The industry standard for object storage. Most features, biggest ecosystem, but egress fees and IAM complexity add up.

SOC 2GDPRHIPAAFedRAMPISO 27001
HIGH Egress fees add up fast HIGH IAM complexity

AWS SES

Choose if: You are already on AWS, sending 50K+ emails/month, and have ops capacity for infrastructure setup.

Amazon's email sending service. Cheapest at scale but complex setup requiring multiple AWS services. Best for teams already on AWS.

SOC 2HIPAAGDPRFedRAMPPCI DSS
HIGH Complex multi-service setup HIGH Sandbox mode by default HIGH Bounce/complaint handling is DIY

AWS SQS

Choose if: You're on AWS and need a fully managed, infinitely scalable message queue with no infrastructure to manage.

Fully managed message queue by AWS. Infinite scale, 1M free requests/month. Enterprise-grade but complex setup.

SOC 2GDPRHIPAAFedRAMPISO 27001PCI DSS
HIGH AWS complexity

Better Auth

Choose if: You want full ownership of auth with zero per-user cost, GDPR-compliant data residency (your database), and the successor to Auth.js.

Open-source TypeScript auth framework. The Auth.js team joined Better Auth in Sept 2025, making it the recommended path forward for Next.js authentication.

HIGH No pre-built UI components

BullMQ

Choose if: You want a battle-tested, zero-cost job queue for Node.js with Redis as the backing store and full control over your infrastructure.

Redis-based job queue for Node.js. Open source, battle-tested, zero recurring cost. The standard self-hosted queue.

GDPR (self-hosted — your data, your region)