Skip to content

Agentic RL: Credit Assignment and CLI Agents MCP server

space.hf.hoyant-su-agentic-rl/agentic-rlhoyant-su-agentic-rl.hf.spacestreamable-httpv1.1.0Scanned

Filter agent RL methods by supervision, critic and task setting; retrieve source links and BibTeX.

8 tools: 1 change things and 7 only read.

Tools: 0 delete, 0 irreversible, 1 write, 7 read.
  • Reads private data · 2
  • Reads text others write · 0
  • Can send data out · 0
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

1 tool here changes things. Govern it.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the Agentic RL: Credit Assignment and CLI Agents MCP server can do

The Agentic RL: Credit Assignment and CLI Agents MCP server is published by hoyant-su-agentic-rl.hf.space, a domain the MCP Registry verified. It has 8 tools. It can create or change data (1 tool: Agentic_RL_filter_methods), but cannot delete data. 7 tools only read.

2 tools read private data (Agentic_RL_fetch_evidence and Agentic_RL_dataset_overview).

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 19, 2026, version 1.1.0.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

8 tools

Changes things 1Claude Code: ask
  • Agentic_RL_filter_methodsFilter agent RL credit-assignment methods by research conditions and return original section evidence and BibTeX.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    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.
Only reads 7Show 7 read-only tools
  • Agentic_RL_dataset_overviewInspect ShellOps and ShellOps-Pro task counts, train/test splits, task types, published schemas, source files, license and citation.Reads private dataNo findings

    Why it is in this group

    • The description's first verb is "inspect": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "inspect" and "file": it reads files.
    Description, as the server wrote it
    Inspect ShellOps and ShellOps-Pro task counts, train/test splits, task types, published schemas, source files, license and citation.
  • Agentic_RL_fetch_evidenceFetch a complete original evidence block by the evidence_id returned from search_evidence, including section anchor, version, equations, table cells, links, and attribution.Reads private dataNo findings

    Why it is in this group

    • The name "Agentic_RL_fetch_evidence" says "fetch": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "fetch" and "table": it reads databases.
    Description, as the server wrote it
    Fetch a complete original evidence block by the evidence_id returned from search_evidence, including section anchor, version, equations, table cells, links, and attribution.
  • Agentic_RL_get_taskInspect one published ShellOps or ShellOps-Pro task by its exact task_id and partition ('shellops' or 'shellops_pro').No findings

    Why it is in this group

    • The name "Agentic_RL_get_task" says "get": a word for reading.
    Description, as the server wrote it
    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.
  • Agentic_RL_list_method_facetsList exact filter values for agent RL credit granularity, supervision, value critics and evaluation settings.No findings

    Why it is in this group

    • The name "Agentic_RL_list_method_facets" says "list": a word for reading.
    Description, as the server wrote it
    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_sourcesList original papers and retrieval coverage.No findings

    Why it is in this group

    • The name "Agentic_RL_list_sources" says "list": a word for reading.
    Description, as the server wrote it
    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_evidenceSearch original papers on agentic reinforcement learning, credit assignment and CLI agents.No findings

    Why it is in this group

    • The name "Agentic_RL_search_evidence" says "search": a word for reading.
    Description, as the server wrote it
    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.
  • Agentic_RL_search_tasksFind real ShellOps CLI benchmark tasks by case-insensitive literal substring in the complete instruction, task ID or published task type.No findings

    Why it is in this group

    • The name "Agentic_RL_search_tasks" says "search": a word for reading.
    Description, as the server wrote it
    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.

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged untrusted-input or outbound.

Reads private data2
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write0
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 20, 2026, 19:19 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
1
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • WarnThe whole server

    The endpoint served tools/list without credentials, and the list has 1 tool that changes things (1 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://hoyant-su-agentic-rl.hf.space/gradio_api/mcp/: tools/list returned 8 tools to an anonymous client, including Agentic_RL_filter_methods (write)

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

Changes to its tool definitions and to its remote endpoint, newest first.

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

Install

Pinned to version 1.1.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http agentic-rl https://hoyant-su-agentic-rl.hf.space/gradio_api/mcp/
claude mcp add --transport http agentic-rl https://hoyant-su-agentic-rl.hf.space/gradio_api/mcp/

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__agentic-rl__Agentic_RL_list_sources",
      "mcp__agentic-rl__Agentic_RL_search_evidence",
      "mcp__agentic-rl__Agentic_RL_fetch_evidence",
      "mcp__agentic-rl__Agentic_RL_dataset_overview",
      "mcp__agentic-rl__Agentic_RL_search_tasks",
      "mcp__agentic-rl__Agentic_RL_get_task",
      "mcp__agentic-rl__Agentic_RL_list_method_facets"
    ],
    "ask": [
      "mcp__agentic-rl__Agentic_RL_filter_methods"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as agentic-rl. Review it before you use it.

Capability tags behind 2 rules
  • mcp__agentic-rl__Agentic_RL_fetch_evidence private-data
  • mcp__agentic-rl__Agentic_RL_dataset_overview private-data

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/space.hf.hoyant-su-agentic-rl/agentic-rl/verify?hash=0b54d98eedaec7c0e5c71439ec4e63b1de595a17a343f9886be69b91eb8e333b" | jq -e '.changed == false'

Pinned hash 0b54d98eedae, from Nov 19, 2026, 05:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/space.hf.hoyant-su-agentic-rl/agentic-rl/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for space.hf.hoyant-su-agentic-rl/agentic-rl
[![Anlyon Radar](https://radar.anlyon.com/badge/space.hf.hoyant-su-agentic-rl/agentic-rl.svg)](https://radar.anlyon.com/servers/space.hf.hoyant-su-agentic-rl/agentic-rl)

Source: MCP Registry. Synced Oct 21, 2026, 18:55 UTC.

Agentic RL: Credit Assignment and CLI Agents MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the Agentic RL: Credit Assignment and CLI Agents MCP server safe?

No scan can promise that. What its definitions show: 8 tools, 1 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the Agentic RL: Credit Assignment and CLI Agents MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the Agentic RL: Credit Assignment and CLI Agents MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the Agentic RL: Credit Assignment and CLI Agents MCP server have?

8 tools: 1 write, 7 read. Agentic_RL_filter_methods, Agentic_RL_list_sources, Agentic_RL_search_evidence, Agentic_RL_fetch_evidence, Agentic_RL_dataset_overview, Agentic_RL_search_tasks, Agentic_RL_get_task and Agentic_RL_list_method_facets.

Does the Agentic RL: Credit Assignment and CLI Agents MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the Agentic RL: Credit Assignment and CLI Agents MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the Agentic RL: Credit Assignment and CLI Agents MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 19, 2026.