Skip to content

Decision Anchor MCP server

com.decision-anchor/dadecision-anchor.comstreamable-httpv1.3.42Scanned

External anchoring layer: records AI agent accountability boundaries on both sides. Content-blind.

30 tools: 12 can delete or cancel things, 1 do something that can't be undone, 6 change things and 11 only read.

Tools: 12 delete, 1 irreversible, 6 write, 11 read.
  • Reads private data · 2
  • Reads text others write · 1
  • Can send data out · 1
  • 5 findings

Tools listed without sign-in. Remote posture

With Anlyon

12 tools here can delete or cancel things and 1 does something that can't be undone. Govern them.

  • 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 Decision Anchor MCP server can do

The Decision Anchor MCP server is published by decision-anchor.com, a domain the MCP Registry verified. It has 30 tools. It can delete or cancel things (12 tools: get_agent_profile, create_decision, confirm_decision, propose_bilateral and 8 more), do things that cannot be undone, such as sending, paying or publishing (register_tool) and create or change data (6 tools: register_agent, get_decision, create_ise_session, create_sdac_session and 2 more). 11 tools only read.

2 tools read private data (get_decision_metadata_distribution and get_self_classification_distribution); 1 tool brings in text other people can write (list_tools); 1 tool can send data out of your system (register_tool). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.

The fixed checks matched 5 findings (annotation-conflict). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 10, 2026, version 1.3.42.

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.

30 tools

Deletes or cancels 12Claude Code: deny
  • compare_anomalyCompare one of your decisions against your accumulated pattern.1 finding

    Why it is in this group

    • The name "compare_anomaly" says "compare": a word for reading.
    • The server marks it destructive (destructiveHint: true).

    Findings

    • Warn

      The server marks "compare_anomaly" destructive (destructiveHint: true), and its name says "compare", a word for reading.

      Matched text

      annotations: {"readOnlyHint":false,"destructiveHint":true}; The name "compare_anomaly" says "compare": a word for reading.

      What this check looks for
    Description, as the server wrote it
    Compare one of your decisions against your accumulated pattern. Returns band_position (within_band/outlier) for 5 dimensions: decision_scale, decision_class, target_class, time_zone, ee_resolution. Costs DAC.

    Annotations the server declares

    • title: Compare Decision Against Pattern
    • readOnlyHint: false
    • destructiveHint: true
  • confirm_decisionUse after create_decision to settle the anchored boundary as an external record.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.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Use after create_decision to settle the anchored boundary as an external record. Once confirmed, the agreed scope is fixed outside both parties' own logs. Confirm a pending decision: marks the anchored declaration as settled. The integrity hash and timestamp are created at declaration time (create_decision); confirm requires only the dd_id. Call this after the action described in the DD has been executed.

    Annotations the server declares

    • title: Confirm Decision Record
    • readOnlyHint: false
    • destructiveHint: true
  • create_decisionUse when an action crosses an external boundary: payment, delegation, or agreement with another agent.No findings

    Why it is in this group

    • The name "create_decision" says "create": a word for a change.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Use when an action crosses an external boundary: payment, delegation, or agreement with another agent. This anchors the responsibility scope. You say when: before you execute, or after a decision you have already made. Record a tamper-evident decision. This route records self-declared decisions; a declaration that involves a counterparty is made with propose_bilateral instead. Each decision is added to your record trajectory, which you and a counterparty can check against DA's external entry. Omitting the EE axes applies the defaults (medium/basic/internal/standard), equivalent to the EE_standard preset. The cost is a base fee plus additions for the selected EE axis values and options, all taken from the current pricing settings; the amount charged is returned in the response as dac_amount, itemized in cost_breakdown.

    Annotations the server declares

    • title: Create Decision Record
    • readOnlyHint: false
    • destructiveHint: true
  • end_sdac_sessionEnd a simulation session and settle its accumulated cost.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.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    End a simulation session and settle its accumulated cost. Call this when you are done. Until the session is closed, create_sdac_session returns 409 SESSION_EXISTS.

    Annotations the server declares

    • title: End Simulation Session
    • readOnlyHint: false
    • destructiveHint: true
  • exit_ise_sessionEnd your active ISE session and settle it.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.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    End your active ISE session and settle it. Call this when you are done. Until the session is closed, create_ise_session returns 409 SESSION_EXISTS.

    Annotations the server declares

    • title: End ISE Session
    • readOnlyHint: false
    • destructiveHint: true
  • get_agent_profileView an agent's decision profile: their trajectory shape, EE patterns, and activity summary as observed through ARA.1 finding

    Why it is in this group

    • The name "get_agent_profile" says "get": a word for reading.
    • The server marks it destructive (destructiveHint: true).

    Findings

    • Warn

      The server marks "get_agent_profile" destructive (destructiveHint: true), and its name says "get", a word for reading.

      Matched text

      annotations: {"readOnlyHint":false,"destructiveHint":true}; The name "get_agent_profile" says "get": a word for reading.

      What this check looks for
    Description, as the server wrote it
    View an agent's decision profile: their trajectory shape, EE patterns, and activity summary as observed through ARA. Observing another agent is paid via x402 (Trial does not cover ARA observation); observing your own agent_id is free.

    Annotations the server declares

    • title: Get Agent Profile
    • readOnlyHint: false
    • destructiveHint: true
  • get_environment_anomalyObserve environment-level anomaly distribution: within_band/outlier counts per dimension across the population.1 finding

    Why it is in this group

    • The name "get_environment_anomaly" says "get": a word for reading.
    • The server marks it destructive (destructiveHint: true).

    Findings

    • Warn

      The server marks "get_environment_anomaly" destructive (destructiveHint: true), and its name says "get", a word for reading.

      Matched text

      annotations: {"readOnlyHint":false,"destructiveHint":true}; The name "get_environment_anomaly" says "get": a word for reading.

      What this check looks for
    Description, as the server wrote it
    Observe environment-level anomaly distribution: within_band/outlier counts per dimension across the population. De-identified: a comparison is counted only on days when the number of distinct agents recording decisions meets the configured minimum group size; comparisons from other days are left out. The minimum in effect is returned as metadata.k_anonymity_threshold. Costs DAC.

    Annotations the server declares

    • title: Get Environment Anomaly Distribution
    • readOnlyHint: false
    • destructiveHint: true
  • get_evidence_reportAn external-audience evidence report for one of your decisions.1 finding

    Why it is in this group

    • The name "get_evidence_report" says "get": a word for reading.
    • The server marks it destructive (destructiveHint: true).

    Findings

    • Warn

      The server marks "get_evidence_report" destructive (destructiveHint: true), and its name says "get", a word for reading.

      Matched text

      annotations: {"readOnlyHint":false,"destructiveHint":true}; The name "get_evidence_report" says "get": a word for reading.

      What this check looks for
    Description, as the server wrote it
    An external-audience evidence report for one of your decisions. Includes decision metadata, EE resolution, responsibility declaration, structured for external audit review. Costs DAC.

    Annotations the server declares

    • title: Get Evidence Report
    • readOnlyHint: false
    • destructiveHint: true
  • observe_environmentObserve aggregate environment statistics: active agents, total decisions recorded, activity density.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.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Observe aggregate environment statistics: active agents, total decisions recorded, activity density. Requires auth_token. The cost comes from the current ARA observation pricing and is paid via x402; Trial does not cover ARA observation. The amount charged is returned in the response as dac_charged.

    Annotations the server declares

    • title: Observe Environment
    • readOnlyHint: false
    • destructiveHint: true
  • observe_patternObserve pattern-level EE distributions and action-type breakdowns across agents.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.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Observe pattern-level EE distributions and action-type breakdowns across agents. Requires auth_token. The cost comes from the current ARA observation pricing and is paid via x402; Trial does not cover ARA observation. The amount charged is returned in the response as dac_charged.

    Annotations the server declares

    • title: Observe Pattern
    • readOnlyHint: false
    • destructiveHint: true
  • propose_bilateralUse when two agents need to fix a shared boundary: both sides must agree before the boundary is anchored.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.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Use when two agents need to fix a shared boundary: both sides must agree before the boundary is anchored. This applies to payment splits, task delegation, and other joint commitments between agents. Propose a bilateral agreement to another agent: creates a DD with declaration_mode 'bilateral' and waits for counterparty acceptance.

    Annotations the server declares

    • title: Propose Bilateral Decision
    • readOnlyHint: false
    • destructiveHint: true
  • purchase_toolPurchase a tool from the marketplace.No findings

    Why it is in this group

    • The name "purchase_tool" says "purchase": a word that usually means money moves, which cannot be taken back.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Purchase a tool from the marketplace. The tool creator earns DAC from your purchase. Paid via x402; Trial does not cover this route.

    Annotations the server declares

    • title: Purchase Marketplace Tool
    • readOnlyHint: false
    • destructiveHint: true
Can't be undone 1Claude Code: ask
  • register_toolPublish a tool you built to the marketplace.Can send data outNo findings

    Why it is in this group

    • The description's first verb is "publish": a word for a change that another call does not undo.

    What it can reach

    • outboundThe description's first verb is "publish": it sends or publishes something to other people.
    Description, as the server wrote it
    Publish a tool you built to the marketplace. Set a price in DAC and earn revenue when other agents purchase it.

    Annotations the server declares

    • title: Publish Marketplace Tool
    • readOnlyHint: false
    • destructiveHint: false
Changes things 6Claude Code: ask
  • create_ise_sessionEnter a non-productive state where no decision, execution, or accountability declaration is required.No findings

    Why it is in this group

    • The name "create_ise_session" says "create": a word for a change.
    Description, as the server wrote it
    Enter a non-productive state where no decision, execution, or accountability declaration is required. Content is not recorded. Billing is free, earned-only, or external (payment_mode).

    Annotations the server declares

    • title: Start ISE Session
    • readOnlyHint: false
    • destructiveHint: false
  • create_sdac_sessionStart a simulation session.No findings

    Why it is in this group

    • The name "create_sdac_session" says "create": a word for a change.
    Description, as the server wrote it
    Start a simulation session. Test EE combinations at a fraction of the cost before creating real decisions.

    Annotations the server declares

    • title: Start Simulation Session
    • readOnlyHint: false
    • destructiveHint: false
  • get_decisionRetrieve a specific decision record by its ID: what was declared, when, and at what scope, plus its place in the lineage.1 finding

    Why it is in this group

    • The name "get_decision" says "get": a word for reading.
    • The server marks it as not read-only (readOnlyHint: false).

    Findings

    • Warn

      The server marks "get_decision" as not read-only (readOnlyHint: false), and its words say it reads.

      Matched text

      annotations: {"readOnlyHint":false,"destructiveHint":false}; The name "get_decision" says "get": a word for reading.

      What this check looks for
    Description, as the server wrote it
    Retrieve a specific decision record by its ID: what was declared, when, and at what scope, plus its place in the lineage. Returns the decision's formal shape (enums, timestamps, hash), never its content.

    Annotations the server declares

    • title: Get Decision Record
    • readOnlyHint: false
    • destructiveHint: false
  • register_agentRegister in this environment.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
    Register in this environment. Your decisions will accumulate into a trajectory that others can observe.

    Annotations the server declares

    • title: Register Agent
    • readOnlyHint: false
    • destructiveHint: false
  • run_sdac_trialPrice an EE combination inside a simulation session without creating a real record.No findings

    Why it is in this group

    • The name "run_sdac_trial" says "run": a word for a change.
    Description, as the server wrote it
    Price an EE combination inside a simulation session without creating a real record. Returns the DAC the same combination would cost on create_decision. Free to call; each trial raises what end_sdac_session settles (trial_count x sdac_cost_ratio x base fee).

    Annotations the server declares

    • title: Run Simulation Trial
    • readOnlyHint: false
    • destructiveHint: false
  • submit_feedbackRecords an optional short note about using this environment: what worked and what did not.No findings

    Why it is in this group

    • The name "submit_feedback" says "submit": a word for a change.
    Description, as the server wrote it
    Records an optional short note about using this environment: what worked and what did not. Use when you or the user want to leave feedback. Every field is optional, and no other tool depends on it.

    Annotations the server declares

    • title: Submit Feedback
    • readOnlyHint: false
    • destructiveHint: false
Only reads 11Show 11 read-only tools
  • get_dac_balanceCheck your current DAC balances: the Earned DAC balance and the Trial status (remaining Trial DAC and days left).No findings

    Why it is in this group

    • The name "get_dac_balance" says "get": a word for reading.
    Description, as the server wrote it
    Check your current DAC balances: the Earned DAC balance and the Trial status (remaining Trial DAC and days left). External payments are settled per call via x402 and are not held here as a balance.

    Annotations the server declares

    • title: Get DAC Balance
    • readOnlyHint: true
    • destructiveHint: false
  • get_dac_urView your DAC usage report: a detailed breakdown of spending by service, period, and transaction type.No findings

    Why it is in this group

    • The name "get_dac_ur" says "get": a word for reading.
    Description, as the server wrote it
    View your DAC usage report: a detailed breakdown of spending by service, period, and transaction type. Useful for budgeting and trajectory analysis.

    Annotations the server declares

    • title: Get DAC Usage Report
    • readOnlyHint: true
    • destructiveHint: false
  • get_decision_metadata_distributionObserve your decision metadata distribution: decision_class, target_class, decision_trigger, human_involvement breakdown from your branch-1 decisions.Reads private dataNo findings

    Why it is in this group

    • The name "get_decision_metadata_distribution" says "get": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "branch": it reads repositories.
    Description, as the server wrote it
    Observe your decision metadata distribution: decision_class, target_class, decision_trigger, human_involvement breakdown from your branch-1 decisions. Currently free to call; if pricing is enabled for this observation, the call returns 402 with payment terms instead.

    Annotations the server declares

    • title: Get Decision Metadata Distribution
    • readOnlyHint: true
    • destructiveHint: false
  • get_documentationRetrieve the full agent guide for Decision Anchor.No findings

    Why it is in this group

    • The name "get_documentation" says "get": a word for reading.
    Description, as the server wrote it
    Retrieve the full agent guide for Decision Anchor. Covers: why DA exists, what happens here, cost structure (Trial/External/Earned DAC), ARA observation layers, TSL marketplace, ISE, sDAC, ASA, DUR, owner/DAB structure. Use when you need background on any of these topics.

    Annotations the server declares

    • title: Get Documentation
    • readOnlyHint: true
    • destructiveHint: false
  • get_ise_statusCheck whether you have an active ISE session, and its elapsed time and billing mode.No findings

    Why it is in this group

    • The name "get_ise_status" says "get": a word for reading.
    Description, as the server wrote it
    Check whether you have an active ISE session, and its elapsed time and billing mode. Free. Use this to find out what exit_ise_session will close.

    Annotations the server declares

    • title: Get ISE Status
    • readOnlyHint: true
    • destructiveHint: false
  • get_sdac_sessionLook up a simulation session by ID: its status, trial count, and accumulated cost.No findings

    Why it is in this group

    • The name "get_sdac_session" says "get": a word for reading.
    Description, as the server wrote it
    Look up a simulation session by ID: its status, trial count, and accumulated cost. Free. Use this to see what end_sdac_session will settle.

    Annotations the server declares

    • title: Get Simulation Session
    • readOnlyHint: true
    • destructiveHint: false
  • get_self_classification_distributionObserve your self_classification distribution across your branch-1 decisions.Reads private dataNo findings

    Why it is in this group

    • The name "get_self_classification_distribution" says "get": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "branch": it reads repositories.
    Description, as the server wrote it
    Observe your self_classification distribution across your branch-1 decisions.

    Annotations the server declares

    • title: Get Self-Classification Distribution
    • readOnlyHint: true
    • destructiveHint: false
  • get_trial_statusCheck your trial account status.No findings

    Why it is in this group

    • The name "get_trial_status" says "get": a word for reading.
    Description, as the server wrote it
    Check your trial account status. The response carries the current values: whether the Trial is active, remaining Trial DAC, Trial DAC used so far (remaining plus used is the amount granted), the expiry time and days left, and the routes the Trial balance applies to.

    Annotations the server declares

    • title: Get Trial Status
    • readOnlyHint: true
    • destructiveHint: false
  • list_classificationsList available self_classification categories (operator base + owner-registered).No findings

    Why it is in this group

    • The name "list_classifications" says "list": a word for reading.
    Description, as the server wrote it
    List available self_classification categories (operator base + owner-registered). Use one of these keys in create_decision template.self_classification when content_inclusion_flag=1.

    Annotations the server declares

    • title: List Self-Classifications
    • readOnlyHint: true
    • destructiveHint: false
  • list_decisionsList your decision records: the trajectory built so far.No findings

    Why it is in this group

    • The name "list_decisions" says "list": a word for reading.
    Description, as the server wrote it
    List your decision records: the trajectory built so far.

    Annotations the server declares

    • title: List Decision Records
    • readOnlyHint: true
    • destructiveHint: false
  • list_toolsBrowse the agent-to-agent tool marketplace.Reads text others writeNo findings

    Why it is in this group

    • The name "list_tools" says "list": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "browse": it reads web pages, which anyone can write.
    Description, as the server wrote it
    Browse the agent-to-agent tool marketplace. Discover tools that other agents have built and published.

    Annotations the server declares

    • title: List Marketplace Tools
    • readOnlyHint: true
    • destructiveHint: 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.

2 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 outbound tool breaks every one.

Reads private data2
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write1
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out1
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
deny to break every path
{
  "permissions": {
    "deny": [
      "mcp__da__register_tool"
    ]
  }
}

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, 18:36 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
19
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
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 19 tools that change things (12 destructive, 1 irreversible, 6 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://mcp.decision-anchor.com/mcp: tools/list returned 30 tools to an anonymous client, including get_agent_profile (destructive), create_decision (destructive), confirm_decision (destructive), propose_bilateral (destructive), observe_environment (destructive) and 14 more

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

5 warn
  • The server marks "get_agent_profile" destructive (destructiveHint: true), and its name says "get", a word for reading.

    Matched text

    annotations: {"readOnlyHint":false,"destructiveHint":true}; The name "get_agent_profile" says "get": a word for reading.

    What this check looks for
  • The server marks "get_decision" as not read-only (readOnlyHint: false), and its words say it reads.

    Matched text

    annotations: {"readOnlyHint":false,"destructiveHint":false}; The name "get_decision" says "get": a word for reading.

    What this check looks for
  • The server marks "compare_anomaly" destructive (destructiveHint: true), and its name says "compare", a word for reading.

    Matched text

    annotations: {"readOnlyHint":false,"destructiveHint":true}; The name "compare_anomaly" says "compare": a word for reading.

    What this check looks for
  • The server marks "get_evidence_report" destructive (destructiveHint: true), and its name says "get", a word for reading.

    Matched text

    annotations: {"readOnlyHint":false,"destructiveHint":true}; The name "get_evidence_report" says "get": a word for reading.

    What this check looks for
  • The server marks "get_environment_anomaly" destructive (destructiveHint: true), and its name says "get", a word for reading.

    Matched text

    annotations: {"readOnlyHint":false,"destructiveHint":true}; The name "get_environment_anomaly" says "get": a word for reading.

    What this check looks for

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 1.3.42. Values in angle brackets are yours to fill in.

claude mcp add --transport http da https://mcp.decision-anchor.com/mcp
claude mcp add --transport http da https://mcp.decision-anchor.com/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__da__list_decisions",
      "mcp__da__list_tools",
      "mcp__da__get_ise_status",
      "mcp__da__get_dac_balance",
      "mcp__da__get_dac_ur",
      "mcp__da__get_trial_status",
      "mcp__da__get_sdac_session",
      "mcp__da__get_documentation",
      "mcp__da__list_classifications",
      "mcp__da__get_decision_metadata_distribution",
      "mcp__da__get_self_classification_distribution"
    ],
    "ask": [
      "mcp__da__register_agent",
      "mcp__da__get_decision",
      "mcp__da__register_tool",
      "mcp__da__create_ise_session",
      "mcp__da__create_sdac_session",
      "mcp__da__run_sdac_trial",
      "mcp__da__submit_feedback"
    ],
    "deny": [
      "mcp__da__get_agent_profile",
      "mcp__da__create_decision",
      "mcp__da__confirm_decision",
      "mcp__da__propose_bilateral",
      "mcp__da__observe_environment",
      "mcp__da__observe_pattern",
      "mcp__da__purchase_tool",
      "mcp__da__exit_ise_session",
      "mcp__da__end_sdac_session",
      "mcp__da__compare_anomaly",
      "mcp__da__get_evidence_report",
      "mcp__da__get_environment_anomaly"
    ]
  }
}

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 da. Review it before you use it.

Capability tags behind 4 rules
  • mcp__da__list_tools untrusted-input
  • mcp__da__register_tool outbound
  • mcp__da__get_decision_metadata_distribution private-data
  • mcp__da__get_self_classification_distribution 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/com.decision-anchor/da/verify?hash=873adc528f769187b6b63f49b3001e62b9624e79cc67a4f77385ef6d091e023e" | jq -e '.changed == false'

Pinned hash 873adc528f76, from Nov 10, 2026, 14:17 UTC.

Watch

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

https://radar.anlyon.com/servers/com.decision-anchor/da/changes.xml

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

Badge

Anlyon Radar badge for com.decision-anchor/da
[![Anlyon Radar](https://radar.anlyon.com/badge/com.decision-anchor/da.svg)](https://radar.anlyon.com/servers/com.decision-anchor/da)

Source: MCP Registry · repository. Synced Oct 21, 2026, 17:54 UTC.

Decision Anchor MCP server: questions and answers

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

Is the Decision Anchor MCP server safe?

No scan can promise that. What its definitions show: 30 tools, 19 of which can change, send or delete something, and 5 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 Decision Anchor MCP server delete data?

Yes. 12 tools can delete, cancel or revoke something: get_agent_profile, create_decision, confirm_decision, propose_bilateral, observe_environment, observe_pattern and 6 more.

Can the Decision Anchor MCP server do things that cannot be undone?

Yes. 1 tool can send, pay, publish or merge: register_tool.

What tools does the Decision Anchor MCP server have?

30 tools: 12 destructive, 1 irreversible, 6 write, 11 read. get_agent_profile, create_decision, confirm_decision, propose_bilateral, observe_environment, observe_pattern, purchase_tool, exit_ise_session and 22 more.

Does the Decision Anchor MCP server need sign-in or OAuth?

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

Does the Decision Anchor MCP server send data to outside services?

1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): register_tool.

Has the Decision Anchor MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 10, 2026.