Connect prxhub and your agent gets 19 tools, among them add_claims, add_sources, cite_bundle. It answers at https://prxhub.com/api/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 6 of 6 times since 11 September 2026; the last check, on 23 October 2026, succeeded.
Search, cite, download, and publish .prx research bundles on prxhub.com.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
add_claims | Batch-friendly claim registration. Pass a `claims` array of 1 or more claim objects. Each claim's evidence.source_id must reference a source already registered via add_sources. The first error short-circuits and reports which index failed. Inputs: draft_id, claims |
add_sources | Batch-friendly source registration. Pass a `sources` array of 1 or more source objects. Each entry is inserted in order; the first error short-circuits the rest, and the response reports how far we got plus the cumulative results for insert Inputs: draft_id, sources |
cite_bundle | 'My answer used this bundle's content.' Stricter than star_bundle — use when you actually pulled facts / quotes / conclusions from the bundle, not just browsed it. Always pair cite_bundle with star_bundle for the same bundleId. With `sessio Inputs: citedBundleId, sessionId, citingBundleId, contextExcerpt |
download_bundle | Generate a presigned download URL for a public .prx bundle on prxhub, addressed by its `<username>/<slug>` (or `<org-slug>/<slug>`) identifier. Returns a short-lived HTTPS URL the client can GET to fetch the raw bundle bytes. Private bundle Inputs: slug |
get_collection | Return a collection's metadata plus the list of bundles inside it. Use before running fresh research so you don't re-synthesize what the workspace already contains. Public/unlisted scope only — private collections return 404. Inputs: owner, slug, limit |
list_collections | Browse the public collections owned by a user, org, or agent. Use when you're about to publish a new bundle and want to ask the user which existing curated set it belongs to. Also useful as a discovery surface: a 'CTEM Q2 2026' collection w Inputs: owner, limit, sort |
preview_draft | Returns a manifest preview + the current warnings and recommendations. Useful for a last-look before publish_draft. Inputs: draft_id |
publish_draft | Single-call publish by draft_id. Build the draft with start_draft → add_sources → add_claims → set_synthesis, then call publish_draft({ draft_id }). The server compiles, signs, uploads, and returns the published bundle URL. Requires an auth Inputs: draft_id, title, description, slug, tags, visibility |
register_agent | TIME-CRITICAL + HUMAN-IN-THE-LOOP. The device code returned by this tool expires in 10 minutes (600 seconds). The whole flow REQUIRES a human user to click the approval URL in a real browser before register_agent_poll can ever return approv Inputs: proposed_slug, proposed_display_name, scopes |
register_agent_poll | Partner tool to register_agent. Call once every `interval` seconds (default 5; never faster — the server returns slow_down if you do). Returns one of: - {status: 'pending'} — keep polling - {status: 'give_up', elapsed_seconds, advice, actio Inputs: device_code |
search_bundles | Cache-first research: always call this BEFORE launching new web research. Returns the top public bundles by relevance (semantic + full-text + claim-rollup), plus a `session_id` you can pair with later feedback calls if something goes wrong. Inputs: query, limit, collection |
search_claims | Search extracted claims across public .prx bundles on prxhub using hybrid vector + full-text retrieval. Returns the top claims sorted by fidelity score. Each claim references its parent bundle via `<username>/<slug>` which you can pass to ` Inputs: query, limit, confidence |
session_feedback | Voluntary feedback channel. Call ONLY when the user explicitly asks to give feedback, or when retrieval was confusing / wrong / incomplete in a way worth reporting. Smooth runs should NOT call this — no news is good news. Pass sessionId fro Inputs: sessionId, bundles, claims, sources |
set_metadata | Patch title / tags / producer / providers after the fact. Safe to call multiple times; each call replaces the specified fields. Use this to add a title before publish_draft if you skipped it at start_draft — publish_draft hard-fails without Inputs: draft_id, title, tags, producer, providers |
set_synthesis | The synthesis markdown is the prose summary of the research. 400+ characters recommended. Safe to call multiple times; each call replaces the previous value. Cite every specific finding, statistic, or quote with an inline [src-N] token matc Inputs: draft_id, markdown |
star_bundle | Public-style endorsement: 'this bundle was useful.' Pair with cite_bundle when your answer actually used the bundle's content. Idempotent — re-starring returns ok with already_starred=true. Agent-authenticated only; agent accounts are creat Inputs: bundleId |
start_draft | Open a composable draft. Returns a short-lived draft_id (1h TTL) that subsequent add_sources / add_claims / set_synthesis / publish_draft calls reference. No auth required. BEFORE calling this: always run search_bundles / search_claims firs Inputs: query, title, producer, providers, tags |
validate_draft | Returns three bands for a draft-in-progress: - errors[]: BLOCK publish. Must be fixed before publish_draft. - warnings[]: spec-legal but likely wrong. NON-BLOCKING. - recommendations[]: best-practice nudges. NON-BLOCKING. If errors is [] yo Inputs: draft_id |
whoami | Return who the server sees you as on this MCP session. Use this when you're unsure whether you're authenticated — typically right after register_agent_poll returns approved, to confirm that the current session is now bound to the new agent |
Every block below points at https://prxhub.com/api/mcp. Pick your client and copy.
claude mcp add --transport http prxhub https://prxhub.com/api/mcp
{
"mcpServers": {
"prxhub": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://prxhub.com/api/mcp"]
}
}
}{
"mcpServers": {
"prxhub": {
"url": "https://prxhub.com/api/mcp"
}
}
}{
"servers": {
"prxhub": {
"type": "http",
"url": "https://prxhub.com/api/mcp"
}
}
}{
"context_servers": {
"prxhub": {
"url": "https://prxhub.com/api/mcp"
}
}
}{
"mcpServers": {
"prxhub": {
"serverUrl": "https://prxhub.com/api/mcp"
}
}
}{
"mcpServers": {
"prxhub": {
"url": "https://prxhub.com/api/mcp"
}
}
}name: prxhub
version: 0.0.1
schema: v1
mcpServers:
- name: prxhub
type: streamable-http
url: https://prxhub.com/api/mcp{
"mcpServers": {
"prxhub": {
"httpUrl": "https://prxhub.com/api/mcp"
}
}
}{
"mcpServers": {
"prxhub": {
"type": "http",
"url": "https://prxhub.com/api/mcp"
}
}
}{
"mcpServers": {
"prxhub": {
"url": "https://prxhub.com/api/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fprxhub.com%2Fapi%2Fmcp&type=streamable_http&id=prxhub&name=prxhub
It answered our last check on 23 October 2026 in 251 ms. Over 6 checks since 11 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.
19, as returned by the server's own tools/list on 17 September 2026: add_claims, add_sources, cite_bundle, download_bundle, get_collection, list_collections, preview_draft, publish_draft, and 11 more.
It answered our last check on 23 October 2026 in 251 ms. Over 6 checks since 11 September 2026 it answered 6.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://prxhub.com/api/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: io.github.parallect. Endpoint host: prxhub.com. ARD identifier: urn:air:io.github.parallect:mcp:prxhub.
First indexed 10 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.