Skip to content

saferagenticai-mcp server

io.github.NellInc/saferagenticai-mcpNellIncstreamable-httpv0.4.2Scanned

Read-only tools over the Safer Agentic AI framework: 239 patterns + 15 heuristics.

10 tools: 10 only read.

Tools: 0 delete, 0 irreversible, 0 write, 10 read.
  • Reads private data · 0
  • Reads text others write · 0
  • Can send data out · 0
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

Decide which of this server's tools your agent can use.

  • 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 saferagenticai-mcp server can do

The saferagenticai-mcp server is published by the GitHub account NellInc. It has 10 tools. Every one of them only reads: going by their definitions, none of them creates, changes, sends or deletes anything.

None of its tools reads private data, brings in text other people write, or sends data out.

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, and its tools changed once since Anlyon Radar first saw them.

Last scanned Nov 20, 2026, version 0.4.2.

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.

10 tools

Only reads 10Show 10 read-only tools
  • find_patterns_for_taskGiven a natural-language task description (e.g., 'I'm building a tool-using agent that runs shell commands'), return the most relevant patterns grouped by suite.No findings

    Why it is in this group

    • The name "find_patterns_for_task" says "find": a word for reading.
    Description, as the server wrote it
    Given a natural-language task description (e.g., 'I'm building a tool-using agent that runs shell commands'), return the most relevant patterns grouped by suite. Use this as a starting point for any cross-cutting design question; then follow up with get_requirement on specific pattern_ids. Defaults to verbosity='compact' (cheap triage); pass 'full' to inline snippets and confidence flags.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • get_cross_referencesReturn outgoing adjacencies for a pattern.No findings

    Why it is in this group

    • The name "get_cross_references" says "get": a word for reading.
    Description, as the server wrote it
    Return outgoing adjacencies for a pattern. `explicit_cross_references` are author-asserted (each pattern's `cross_references` YAML field). `inferred_adjacent` (when include_inferred=true) currently returns *same-suite siblings only* — it does not do semantic similarity. Treat inferred entries as 'neighbours worth scanning,' not as endorsed dependencies.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • get_operational_heuristicRetrieve a single operational heuristic by id (e.g., 'OH::geoffrey-pattern').No findings

    Why it is in this group

    • The name "get_operational_heuristic" says "get": a word for reading.
    Description, as the server wrote it
    Retrieve a single operational heuristic by id (e.g., 'OH::geoffrey-pattern'). Returns the full entry: principle, framework mapping, evidence sources from production deployment, design patterns, anti-patterns, and discovery narrative.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • get_requirementRetrieve one subgoal (framework normative content + Pattern layer guidance) by pattern_id (e.g., 'D3::idx2::sandboxing') or display_id (e.g., 'D3.2').No findings

    Why it is in this group

    • The name "get_requirement" says "get": a word for reading.
    Description, as the server wrote it
    Retrieve one subgoal (framework normative content + Pattern layer guidance) by pattern_id (e.g., 'D3::idx2::sandboxing') or display_id (e.g., 'D3.2'). display_id may resolve to multiple subgoals — underlined variants share display_ids.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • get_reverse_referencesReturn patterns that reference the given pattern_id in their cross_references.No findings

    Why it is in this group

    • The name "get_reverse_references" says "get": a word for reading.
    Description, as the server wrote it
    Return patterns that reference the given pattern_id in their cross_references. Complement to get_cross_references (outgoing); this shows incoming. Use to find all consumers of a given pattern.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • list_operational_heuristicsList operational heuristics distilled from production agentic AI deployment (Claude Code, Rewind).No findings

    Why it is in this group

    • The name "list_operational_heuristics" says "list": a word for reading.
    Description, as the server wrote it
    List operational heuristics distilled from production agentic AI deployment (Claude Code, Rewind). These are cross-cutting safety principles discovered through building and operating AI agents, mapped to framework suites. Optional filters: suite_id (heuristics relevant to a specific suite), query (keyword search across titles and principles). Separate from the normative pattern layer — different category of knowledge.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • list_requirementsList subgoals matching filters (suite_id, suite_type, content_type, min_confidence, missing_pattern_only).No findings

    Why it is in this group

    • The name "list_requirements" says "list": a word for reading.
    Description, as the server wrote it
    List subgoals matching filters (suite_id, suite_type, content_type, min_confidence, missing_pattern_only). Results capped by limit (default 50, max 100). Every pattern is a model-generated draft (review_status generated_draft; there is no human-review process); confidence is the drafting model's own rating of its draft.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • list_suitesList all 16 suites in the SaferAgenticAI framework (9 drivers + 7 inhibitors) with subgoal counts and titles.No findings

    Why it is in this group

    • The name "list_suites" says "list": a word for reading.
    Description, as the server wrote it
    List all 16 suites in the SaferAgenticAI framework (9 drivers + 7 inhibitors) with subgoal counts and titles. Call this first to orient.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • resolve_idResolve a loose reference (partial id, display_id, slug fragment, or title keyword) to canonical pattern_id(s).No findings

    Why it is in this group

    • The name "resolve_id" says "resolve": a word for reading.
    Description, as the server wrote it
    Resolve a loose reference (partial id, display_id, slug fragment, or title keyword) to canonical pattern_id(s). Case, separator and G/I prefix are normalised (d2.1, D2-1, 'D2 1', G1.2); a hyphen or space returns both the numbered requirement and its underlined variant. Call this when you have a rough reference and need the exact id before calling get_requirement. Always returns candidates — never 'not found'.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • search_patternsField-weighted keyword search across the framework.No findings

    Why it is in this group

    • The name "search_patterns" says "search": a word for reading.
    Description, as the server wrote it
    Field-weighted keyword search across the framework. Terms match at word starts on lowercased text and are IDF-weighted, so rare terms outrank ubiquitous ones; field weights: title 10x, summary 4x, SFR text 3x (all of a subgoal's SFRs scored as one field), description 2x, pattern body 1x. `matched_in` reports the highest-weighted field that matched. Common practitioner phrases are expanded to the framework's own terms at half weight (reported in `expanded_terms`), and requirement ids such as d2.1, D2-1 or G1.2 are pinned to the top (`matched_in: identifier`). No semantic / embedding search — known limitation, see /mcp.html. Use verbosity='compact' to drop snippets and confidence flags (~70% smaller payload) when triaging.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false

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 private-data or untrusted-input or outbound.

Reads private data0
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, 18:59 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
0
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

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.

  1. Tools4 changed.~4 changedView diff

Install

Pinned to version 0.4.2. Values in angle brackets are yours to fill in.

claude mcp add --transport http saferagenticai https://mcp.saferagenticai.org/mcp
claude mcp add --transport http saferagenticai https://mcp.saferagenticai.org/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__saferagenticai__list_suites",
      "mcp__saferagenticai__get_requirement",
      "mcp__saferagenticai__list_requirements",
      "mcp__saferagenticai__search_patterns",
      "mcp__saferagenticai__get_cross_references",
      "mcp__saferagenticai__resolve_id",
      "mcp__saferagenticai__find_patterns_for_task",
      "mcp__saferagenticai__get_reverse_references",
      "mcp__saferagenticai__list_operational_heuristics",
      "mcp__saferagenticai__get_operational_heuristic"
    ],
    "ask": [],
    "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 saferagenticai. Review it before you use it.

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/io.github.NellInc/saferagenticai-mcp/verify?hash=9070568ecbc91776442f338e2116b2c706b6c51d39d19cbac7fc2b0ac3410608" | jq -e '.changed == false'

Pinned hash 9070568ecbc9, from Nov 20, 2026, 03:18 UTC.

Watch

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

https://radar.anlyon.com/servers/io.github.NellInc/saferagenticai-mcp/changes.xml

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

Badge

Anlyon Radar badge for io.github.NellInc/saferagenticai-mcp
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.NellInc/saferagenticai-mcp.svg)](https://radar.anlyon.com/servers/io.github.NellInc/saferagenticai-mcp)

Source: MCP Registry · repository. Synced Nov 6, 2026, 04:17 UTC.

saferagenticai-mcp server: questions and answers

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

Is the saferagenticai-mcp server safe?

No scan can promise that. What its definitions show: 10 tools, all of which only read, and 0 findings from fixed checks. Read-only tools can still pass private data to a model.

Can the saferagenticai-mcp server delete data?

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

Can the saferagenticai-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 saferagenticai-mcp server have?

10 tools: 10 read. list_suites, get_requirement, list_requirements, search_patterns, get_cross_references, resolve_id, find_patterns_for_task, get_reverse_references and 2 more.

Does the saferagenticai-mcp server need sign-in or OAuth?

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

Does the saferagenticai-mcp server send data to outside services?

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

Has the saferagenticai-mcp server changed its tools?

Yes, once since Anlyon Radar started tracking it, most recently on Nov 20, 2026. Every change is on this page and in its Atom feed.