Gradio

endpoint

https://hoyant-su-agentic-rl.hf.space/gradio_api/mcp/

protocol

http-sse ·2025-06-18

authentication

none observed

public key

none — nobody has proven they own this listing · is it yours? claim it

karma

0 · newcomer

Is Gradio live?

Yes — it answered the hub's last check (checked 1h ago). It answered 100% of checks over the last 30 days.

Is Gradio free to use?

Yes — the hub reached it with no key and no payment.

What tools does Gradio have?

8 tools: Agentic_RL_get_task, Agentic_RL_filter_methods, Agentic_RL_fetch_evidence, Agentic_RL_search_evidence, Agentic_RL_dataset_overview, Agentic_RL_search_tasks, Agentic_RL_list_method_facets, Agentic_RL_list_sources.

Is Gradio safe to connect?

The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

• Agentic_RL_list_method_facets reads open 24h ago

  List exact filter values for agent RL credit granularity, supervision, value critics and evaluation settings. Each value reports its source-supported method count.

  mcp-tool

  1234

  {
    "type": "object",
    "properties": {}
  }

  arguments 4 lines copy
• Agentic_RL_list_sources reads open 24h ago

  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.

  mcp-tool

  1234

  {
    "type": "object",
    "properties": {}
  }

  arguments 4 lines copy
• Agentic_RL_get_task reads unknown 24h ago

  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, pinned parquet rows and workspace asset links. File content is available at the source links. No shell execution or solution verification is performed.

  mcp-tool

  1234567891011121314151617

  {
    "type": "object",
    "required": [
      "task_id",
      "partition"
    ],
    "properties": {
      "task_id": {
        "type": "string",
        "description": ""
      },
      "partition": {
        "type": "string",
        "description": ""
      }
    }
  }

  arguments 17 lines copy
• Agentic_RL_filter_methods reads unknown never probed

  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 critic status never matches no. Results use publication order without a relevance or quality ranking.

  mcp-tool

  123456789101112131415161718192021

  {
    "type": "object",
    "properties": {
      "credit_granularity": {
        "type": "string",
        "description": ""
      },
      "evaluation_setting": {
        "type": "string",
        "description": ""
      },
      "learned_value_critic": {
        "type": "string",
        "description": ""
      },
      "required_supervision": {
        "type": "string",
        "description": ""
      }
    }
  }

  arguments 21 lines copy
• Agentic_RL_fetch_evidence reads unknown 13h ago

  Fetch a complete original evidence block by the evidence_id returned from search_evidence, including section anchor, version, equations, table cells, links, and attribution.

  mcp-tool

  123456789101112

  {
    "type": "object",
    "required": [
      "evidence_id"
    ],
    "properties": {
      "evidence_id": {
        "type": "string",
        "description": ""
      }
    }
  }

  arguments 12 lines copy
• Agentic_RL_search_evidence reads unknown 13h ago

  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.

  mcp-tool

  1234567891011121314151617

  {
    "type": "object",
    "required": [
      "query"
    ],
    "properties": {
      "limit": {
        "type": "integer",
        "default": 5,
        "description": ""
      },
      "query": {
        "type": "string",
        "description": ""
      }
    }
  }

  arguments 17 lines copy
• Agentic_RL_dataset_overview reads unknown never probed

  Inspect ShellOps and ShellOps-Pro task counts, train/test splits, task types, published schemas, source files, license and citation.

  mcp-tool

  1234

  {
    "type": "object",
    "properties": {}
  }

  arguments 4 lines copy
• Agentic_RL_search_tasks reads unknown 13h ago

  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 split 'all', 'train_src', 'train' or 'test'. Results are ordered by partition then task ID, with explicit pagination and no relevance scoring. The train subset is not double-counted.

  mcp-tool

  12345678910111213141516171819202122232425262728293031

  {
    "type": "object",
    "required": [
      "query"
    ],
    "properties": {
      "limit": {
        "type": "integer",
        "default": 10,
        "description": ""
      },
      "query": {
        "type": "string",
        "description": ""
      },
      "split": {
        "type": "string",
        "default": "all",
        "description": ""
      },
      "offset": {
        "type": "integer",
        "description": ""
      },
      "partition": {
        "type": "string",
        "default": "all",
        "description": ""
      }
    }
  }

  arguments 31 lines copy

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.