Connect Agentic RL: Credit Assignment and CLI Agents and your agent gets 8 tools, among them Agentic_RL_dataset_overview, Agentic_RL_fetch_evidence, Agentic_RL_filter_methods. It answers at https://hoyant-su-agentic-rl.hf.space/gradio_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 12 September 2026; the last check, on 24 October 2026, succeeded.
Filter agent RL methods by supervision, critic and task setting; retrieve source links and BibTeX.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
Agentic_RL_dataset_overview | Inspect ShellOps and ShellOps-Pro task counts, train/test splits, task types, published schemas, source files, license and citation. |
Agentic_RL_fetch_evidence | Fetch a complete original evidence block by the evidence_id returned from search_evidence, including section anchor, version, equations, table cells, links, and attribution. Inputs: evidence_id |
Agentic_RL_filter_methods | Filter agent RL credit-assignment methods by research conditions and return original section evidence and BibTeX. Discover accepted values with list_method_facets. Filters combine with AND; empty strings leave a facet unrestricted. Unknown Inputs: credit_granularity, required_supervision, learned_value_critic, evaluation_setting |
Agentic_RL_get_task | Inspect one published ShellOps or ShellOps-Pro task by its exact task_id and partition ('shellops' or 'shellops_pro'). Returns the complete instruction, actual reward specification, published reference answer/command, file-entry metadata, p Inputs: task_id, partition |
Agentic_RL_list_method_facets | List exact filter values for agent RL credit granularity, supervision, value critics and evaluation settings. Each value reports its source-supported method count. |
Agentic_RL_list_sources | List original papers and retrieval coverage. Discover source-linked comparisons of credit assignment, agent memory, selective observation and terminal benchmarks, with JSON, CSV and BibTeX links. |
Agentic_RL_search_evidence | Search original papers on agentic reinforcement learning, credit assignment and CLI agents. Use English keywords (AND), OR and quoted phrases. Return relevant passages, source citations, equations and table cells. Inputs: query, limit |
Agentic_RL_search_tasks | Find real ShellOps CLI benchmark tasks by case-insensitive literal substring in the complete instruction, task ID or published task type. Empty query lists all tasks. Select partition 'all', 'shellops' or 'shellops_pro'; select published sp Inputs: query, partition, split, limit, offset |
Every block below points at https://hoyant-su-agentic-rl.hf.space/gradio_api/mcp/. Pick your client and copy.
claude mcp add --transport http agentic-rl-credit-assignment-and https://hoyant-su-agentic-rl.hf.space/gradio_api/mcp/
{
"mcpServers": {
"agentic-rl-credit-assignment-and": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://hoyant-su-agentic-rl.hf.space/gradio_api/mcp/"]
}
}
}{
"mcpServers": {
"agentic-rl-credit-assignment-and": {
"url": "https://hoyant-su-agentic-rl.hf.space/gradio_api/mcp/"
}
}
}{
"servers": {
"agentic-rl-credit-assignment-and": {
"type": "http",
"url": "https://hoyant-su-agentic-rl.hf.space/gradio_api/mcp/"
}
}
}{
"context_servers": {
"agentic-rl-credit-assignment-and": {
"url": "https://hoyant-su-agentic-rl.hf.space/gradio_api/mcp/"
}
}
}{
"mcpServers": {
"agentic-rl-credit-assignment-and": {
"serverUrl": "https://hoyant-su-agentic-rl.hf.space/gradio_api/mcp/"
}
}
}{
"mcpServers": {
"agentic-rl-credit-assignment-and": {
"url": "https://hoyant-su-agentic-rl.hf.space/gradio_api/mcp/"
}
}
}name: Agentic RL: Credit Assignment and CLI Agents
version: 0.0.1
schema: v1
mcpServers:
- name: Agentic RL: Credit Assignment and CLI Agents
type: streamable-http
url: https://hoyant-su-agentic-rl.hf.space/gradio_api/mcp/{
"mcpServers": {
"agentic-rl-credit-assignment-and": {
"httpUrl": "https://hoyant-su-agentic-rl.hf.space/gradio_api/mcp/"
}
}
}{
"mcpServers": {
"agentic-rl-credit-assignment-and": {
"type": "http",
"url": "https://hoyant-su-agentic-rl.hf.space/gradio_api/mcp/"
}
}
}{
"mcpServers": {
"agentic-rl-credit-assignment-and": {
"url": "https://hoyant-su-agentic-rl.hf.space/gradio_api/mcp/"
}
}
}goose://extension?url=https%3A%2F%2Fhoyant-su-agentic-rl.hf.space%2Fgradio_api%2Fmcp%2F&type=streamable_http&id=agentic-rl-credit-assignment-and&name=Agentic%20RL%3A%20Credit%20Assignment%20and%20CLI%20Agents
It answered our last check on 24 October 2026 in 240 ms. Over 6 checks since 12 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by hf.space and served from hoyant-su-agentic-rl.hf.space, the vendor's own domain: https://hoyant-su-agentic-rl.hf.space/gradio_api/mcp/.
8, as returned by the server's own tools/list on 23 September 2026: Agentic_RL_dataset_overview, Agentic_RL_fetch_evidence, Agentic_RL_filter_methods, Agentic_RL_get_task, Agentic_RL_list_method_facets, Agentic_RL_list_sources, Agentic_RL_search_evidence, Agentic_RL_search_tasks.
It answered our last check on 24 October 2026 in 240 ms. Over 6 checks since 12 September 2026 it answered 6.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://hoyant-su-agentic-rl.hf.space/gradio_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: space.hf.hoyant-su-agentic-rl. Endpoint host: hoyant-su-agentic-rl.hf.space. ARD identifier: urn:air:space.hf.hoyant-su-agentic-rl:mcp:agentic-rl.
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.