| FMRS | 46 / 100 · D | 75 / 100 · B |
|---|
| Reliability | 6 / 20 | 13 / 20 |
|---|
| Security and permissions | 8 / 20 | 12 / 20 |
|---|
| Maintenance | 10 / 20 | 16 / 20 |
|---|
| Documentation | 12 / 20 | 17 / 20 |
|---|
| Setup experience | 10 / 20 | 17 / 20 |
|---|
| Best for | - LLM users and analysts who need Brazilian public procurement open data
- Developers using Claude Desktop, Cursor, Continue, Cline/Roo Code, or Zed
- Govtech, compliance, supplier intelligence, and bidding researchers
- Teams wanting keyless, signup-free access to PNCP and CNPJ public data
| - Scenarios needing clean, structured web context fed to an AI assistant
- Users already on the Firecrawl platform who want to call its scraping capability directly via MCP
|
|---|
| Not for | - Users needing Licinexus's proprietary matchmaking engine, supplier scoring, price aggregation, or AI-generated artifacts
- Scenarios requiring an official SLA or paid support (this is a community project, best effort, no SLA)
- Users expecting access to private databases or non-public data
- ChatGPT web users, since the consumer web app does not support MCP stdio
| - Simple static-page scraping where you don't want to depend on a third-party API and incur call costs
- Sites that explicitly disallow automated access (robots.txt)
|
|---|
| Required permissions | - Network access to public HTTPS endpoints: PNCP and BrasilAPI (or MinhaReceita)
- Local execution: downloads and runs the npm package @licinexusbr/mcp via npx, using the local npm cache (e.g. ~/.npm/_npx/)
- Process communication: JSON-RPC over stdin/stdout with the MCP client
- In-memory local cache: short-TTL LRU caching of heavy responses
- Optional environment variables: CNPJ_PROVIDER (brasilapi default or minhareceita), LICINEXUS_LOG_LEVEL, LICINEXUS_LANG
- No API keys or account credentials required
| - Requires a Firecrawl API key to call; cost and quota are governed by the Firecrawl account
- firecrawl_agent/firecrawl_interact perform automated browser interaction, which may trigger login or form-submission flows on the target site
|
|---|
| Risks and side effects | - Data comes from public government APIs; PNCP can take 15–30 seconds to respond, and broad queries may time out
- Public data may be delayed, missing, or inconsistent, so LLM output needs human review and should not be the sole basis for legal or bidding decisions
- npx downloads and executes a third-party npm package, so supply-chain risk depends on the trustworthiness of that package's publishing channel
- npx caching may run an older version unless @latest is specified
- Using an absolute npx path from which npx writes a local machine path into your config file
- Debug logging may include query parameters, so avoid exposing sensitive context
| - Bulk crawl/map tools can generate significant request volume against a target site — respect the site's rate limits and terms of service
- firecrawl_agent's interactive action chain is longer — define task boundaries clearly before running it to avoid accidentally triggering actions on a sensitive site
|
|---|
| Supported clients | Claude Desktop, Cursor, Continue, Cline, Roo Code, Zed, ChatGPT | Claude Desktop, VS Code, Cursor, Windsurf, Zed, Amp |
|---|
| Tools | 18 | 11 |
|---|