A side-by-side look at the AllMCPs Server and Comprot: Processo MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose AllMCPs Server for aggregators work over a hosted endpoint; choose Comprot: Processo for legal over a hosted endpoint. You can also run both side by side in one mcpServers block.
ALLMCPS_MCP_URL.search_mcp_servers, get_mcp_install_config, get_mcp_alternatives.comprot_processo_consultar, show_version, report_bug.Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Aggregators | Legal |
| Quality signal | 85/100 · Excellent | 39/100 · Fair |
| Install command | Confirmed | Confirmed |
| Transport | Remote HTTP/SSE | Remote HTTP/SSE |
| Auth | No auth required | Not declared |
| Pricing | Free | Not declared |
| Required env vars | ALLMCPS_MCP_URL | None listed |
| Verified owner | Verified | Community listing |
| GitHub stars | 4 | 0 |
| Directory activity | 69 views 20 installs 1 upvotes | 1 views 0 installs 0 upvotes |
| Tools | 13 | 7 |
| Full listing | View AllMCPs Server | View Comprot: Processo |
search_mcp_serversSearch the AllMCPs directory for Model Context Protocol (MCP) servers by keyword or category.get_mcp_install_configGet setup for one MCP server by ID: the config for every major client (Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Cline, Zed, Codex, Gemini CLI, JetBrains, Roo Code, Continue, LM Studio) plus its documentation. Pass `client` for just one.get_mcp_alternativesList alternative MCP servers to a given server ID — same category, ranked by fit and evidence that they work.compare_mcp_serversCompare 2 to 4 MCP servers side by side: transport, install command, evidence they work, tool count and source, health, GitHub stars, last commit and quality score.recommend_mcp_stackRecommend a small stack of complementary MCP servers for a role or workflow (e.g. "fullstack web app", "data science", "devops on AWS"), drawn from a live directory search.list_mcp_categoriesList all categories available in the AllMCPs directory along with server counts.get_boost_pricingGet pricing and features for boosting / featuring an MCP server on AllMCPs.com.boost_mcp_serverInitiate a sponsorship / boost order for an MCP server by ID, returning a Stripe checkout session URL and x402 invoice.get_boost_statusCheck current boost status, verified badge level, and sponsorship expiration for an MCP server by ID.submit_mcp_serverProgrammatically submit a new MCP server repository to AllMCPs.com for indexing and review. Supports the same optional enrichment fields as the human submission form — fill in whichever you can confidently determine from the repository (README, package.json, code) to produce a fully flushed-out listing. Omit anything you are not confident about rather than guessing; all enrichment fields are optional and unrecognized enum values are simply dropped, not rejected.verify_mcp_claimVerify ownership and claim an MCP server listing by checking GitHub README badge, website badge, or DNS TXT record. Works two ways: (1) fully unattended — pass `agentToken` from confirm_mcp_agent (or set an `Authorization: Bearer <token>` header if your client supports it), no human sign-in needed; or (2) if called with neither, requires the caller to already have an active AllMCPs browser session. Unattended agents should use register_mcp_agent + confirm_mcp_agent first.register_mcp_agentStart unattended-agent registration: emails a 6-digit confirmation code to the given address. Follow up with confirm_mcp_agent to exchange the code for a bearer token, which unlocks verify_mcp_claim (and future privileged tools) without ever needing a human to sign in via browser.comprot_processo_consultarComprot: Processo, consulta em fonte oficial. Hospedado pela plataforma, sem credenciais da plataforma, pague por consulta com crédito pré-pago. Consulta informação de fontes e órgãos oficiais brasileiros (a mesma disponível ao cidadão), não é dado sigiloso. O cliente é o controlador dos dados e responde pela finalidade legítima (LGPD).show_versionShow the current MCP platform and adapter versions.report_bugReport a bug, missing feature, or send feedback. Include the conversation array with recent messages for reproduction.connectReturns connection status and URLs. When all providers are connected, returns authenticated:true and empty pending[]. When credentials are missing, returns connect_url for the toolkit and per-install URLs.toolkit_infoReturns the current toolkit state: installed MCPs, their connection status, the accounts connected to each one, and how many catalog tools each exposes.marketplaceThe official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them. Covers capability requests like "find an MCP that does X", "consulta um CPF", "is there a tool for Y". Core flow: action=search discovers MCPs by intent → describe returns one MCP's full profile (every tool with its id + params, pricing, auth) so you pick the right tool_id → invoke RUNS that tool. KEY: invoke works even when the MCP is NOT installed — it runs the tool pontualmente (one-off), without adding the MCP to the toolkit and without bloating the tool list. If the MCP needs a credential/login, invoke returns a connect link; if it is paid and the wallet is empty, invoke returns a checkout/top-up link (the user opens it, then you retry). Use install only to make an MCP PERMANENT in the active toolkit (its tools then show up natively in future sessions); prefer invoke for a single/occasional use. list_tools lists what is callable right now. subscribe/cancel handle per-MCP billing; report_bug sends feedback; request_mcp asks us to build a NEW MCP when nothing fits. Search/describe flag installed_in_toolkit vs installed_in_workspace. Writes (install/uninstall/subscribe/cancel and the one-off install behind invoke) require workspace owner/admin. It also carries the mcp.ai PROMPT LIBRARY, which is about ready-made prompt TEXT rather than MCPs: search_prompts finds one, get_prompt returns its full text with {{variables}} filled, and publish_prompt saves a prompt and returns a shareable mcp.ai/p/<slug> link that opens without login.authenticateMCP.AI for IDE agents (Cursor, etc.): log in in the browser, copy the access token. Best: add it to this server's config as a header `Authorization: Bearer <token>` for a permanent, non-expiring connection. Or paste it here for a session-only login: call with { token: "<jwt>" } after the user pastes, or with no args to get the link.Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
{
"mcpServers": {
"allmcps-server": {
"command": "npx",
"args": [
"-y",
"allmcps-server"
],
"env": {
"ALLMCPS_MCP_URL": "YOUR_ALLMCPS_MCP_URL_HERE"
}
}
}
}
{
"mcpServers": {
"comprot-processo": {
"url": "https://api.mcp.ai/p_comprot_processo"
}
}
}