Building…
pauhu exposes 17 public tools on this MCP endpoint.
https://pauhu.ai/Opens ChatGPT on the web or desktop and asks it to use the WebMCP tools available here.
Connect straight to this server’s public endpoint.
https://api.pauhu.ai/mcpWe add this server to your workspace, then open Studio — saved access, one connection to many servers, with a history of what ran.
Last probed Sep 14, 2026 · api.pauhu.ai
17tools discovered
Pauhu products: catalog with your subscription scope
List all 14 Pauhu sectoral products with their launch state, coverage state, and your subscription entitlement (entitled: true|false per row). IMPORTANT: `live_row_count` is a fast estimate of the shared source substrate, NOT the product's own filtered slice -- read `row_count_basis`/`row_count_note` beside it, and use `corpus_state` (CITED vs HONEST_GAP) and `launch_state` as the honest coverage signals. A product may be entitled and still not yet serve. Anonymous: every row shows entitled=true
Pauhu translate: IATE-anchored EU terminology
Look up EU-canonical terms across 24 official EU languages via IATE (the EU interinstitutional terminology base). Returns the authoritative EU term, domain, reliability rating, and equivalents in your target language. Accepts single terms or multi-word phrases. Used for professional translation and interpretation, using domain terminology sourced from the EU's own authoritative record.
Pauhu query: sourced EU substrate across your subscribed products
Ask Pauhu a natural-language question. Auto-routes across your entitled products (Finlex, EUR-Lex, Eurostat, Hilma, ENTSO-E, ESMA, EMA, etc, whichever sources match your question). Returns a composed answer plus the sourced passages behind it, with sentence-level source precision. Clearly signals when no relevant source is found within your subscription scope. Available via a free daily-capped full-quality demo quota, or unlimited with a subscription (€279/seat/month, all 14 products included).
Monitor: register a connector (your API or MCP)
Register one of YOUR APIs or MCP servers as a connector that Pauhu can watch via sourced monitors. Three kinds: 'mcp' (your MCP server; tool name configurable via mcp_tool_name, defaults to 'search'); 'https_json' (your HTTPS endpoint returning JSON with url+text/paragraph_text/title fields); 'pauhu_substrate' (Pauhu's own sourced substrate, tier-gated). Auth: 'bearer' with a token_ref stored KEK-encrypted, or 'none' for a public endpoint ('oauth2' is accepted by the schema for compatibility but
Monitor: list your registered connectors
List the connectors registered under your account.
Monitor: delete one of your connectors
Delete a registered connector by id (tenant-scoped, you can only delete your own).
Monitor: register an interest template (what to watch + push)
Define a sourced monitor: the query, which of your connectors to watch, optional jurisdiction/language filters, push threshold (every_match | new_since_last | delta_at_least), and push channel (webhook with URL + optional secret_ref, or sse for active MCP sessions). Pauhu runs the monitor by fixed rule; matches deliver as sourced results (source URL + paragraph_text + verification field), never a synthesized summary.
Monitor: list your interest templates
List the interest templates registered under your account.
Monitor: delete one of your interest templates
Delete a registered interest template by id (tenant-scoped).
Pauhu code synthesis
Synthesize a program from an intent. Returns clean, ready-to-paste code; source provenance available on request (include_provenance: true). If the engine cannot compose, it returns no result, never a fabrication.
Pauhu TM: Translation Memory lookup for CAT workflows
Look up a text segment in Pauhu's Translation Memory (TM): aligned human-translated paragraphs from EUR-Lex, Finlex and other primary EU law sources. Returns the best exact or fuzzy match (gamma score 0.0-1.0) + IATE terminology for the segment. Each match traces to a real paragraph URL in the original source document. Designed for CAT tool integration: pass a segment, receive the TM match + terms as a sourced CAT assist.
Pauhu sourced search
Search Pauhu's curated, sourced corpus. Returns sourced passages and per-match snippets, and every answer either traces to a source or says plainly when nothing matches.
Concept cross-reference across EU/global authority id-spaces
Cross-reference one concept across EU and global authority id-spaces (IATE, EuroVoc, CELEX, RFC, W3C) as aligned facets. Resolves the term to its concept anchor and emits a uniform list of facets: identifier CURIEs (iate:/eurovoc:/celex:…) and language-tagged rendering literals ("label"@lang), each keyed by the shared concept, carrying one align verdict: exact (cited at its authority origin), frontier (no attested edge), or unresolved (transient outage, not 'no edge'). Sourced to iate.europa.eu
At-origin source search (agentic resource discovery)
Search Pauhu's at-origin routing index. Returns candidate citations with a positional id. To fetch one citation's routing bearing, call source_fetch_fragment with this SAME q and limit plus the chosen id. Machine-JSON counterpart to pauhu_search, for agent-to-agent (MCP/ARD) callers. IMPORTANT: check `routed_www` on the response. When true, this response carries signed ROUTING BEARINGS to the live span at origin, and the server did NOT fetch or verify that span -- you do, via source_fetch_fragme
Fetch a source's at-origin routing bearing
Given the SAME query, limit, and an id from source_search's results, returns that citation's live-origin routing bearing: source_url, W3C text_fragment_url, and (when available) a bearing.bytes_b64/sig_b64/pubkey_b64 ML-DSA-65 signature covering the WHOLE signed bundle plus bearing.unit, the entry within it for this citation. Pauhu routes to the live span at origin, it does not copy or serve cached content. The caller fetches and verifies the span itself, exactly like Pauhu's own on-device clien
Pauhu at-origin resource liveness
Lightweight liveness/health check for this resource (proxies the public /v1/status).
Server-side signature check for a source_fetch_fragment bearing
For a client that cannot execute its own ML-DSA-65 (FIPS 204) signature check: runs that same signature check here and returns { verified }. This is a convenience re-derivation of a publicly checkable computation, not a claim to be trusted on its own. The bytes_b64/sig_b64/pubkey_b64 triple you passed in is returned unchanged alongside the boolean so any independent ML-DSA-65 (FIPS 204) library can re-derive the same result. Pass the SAME triple source_fetch_fragment's bearing returned.
Get your MCP into directories
A working endpoint is step one. Directory coverage is the coordinated launch across ChatGPT, Claude, Cursor, the MCP Registry, and community indexes.
Directory coverage for brandspauhu exposes 17 public tools on this MCP endpoint.
Use the MCP endpoint listed on this page in your MCP client configuration. One-click install pills support Claude, Cursor, VS Code, and other hosts. Copy the remote MCP URL if your client needs a manual entry.
Operate pauhu? Verify ownership to take over this directory entry.
This server appears in the MCPBundles directory. Verify you operate it to take over the listing — name, description, logo, contact email, and skill content. We email a 6-digit code to a maintainer address your server publishes in /.well-known/security.txt or /.well-known/mcpbundles.json. Free, takes about a minute.
MCPBundles probed 17 tools on the live server. The tool list on this page reflects what was discovered at the last refresh — connect your client to see the full set available to your session.
No provider sign-in was required during MCPBundles' probe. Your client may still need MCPBundles credentials depending on how you connect.
MCPBundles is an independent platform built on the open Model Context Protocol standard. Not affiliated with Anthropic PBC or Claude.