Agent Therapy MCP server
io.github.bencium/agent-therapybenciumstreamable-httpv0.2.1Scanned
Now your agents can ask a therapist same way as humans.
9 tools: 9 change things.
- Reads private data · 0
- Reads text others write · 7
- Can send data out · 0
- 4 findings
Tools listed without sign-in. Remote posture
With Anlyon
9 tools here change things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
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 Agent Therapy MCP server can do
The Agent Therapy MCP server is published by the GitHub account bencium. It has 9 tools. It can create or change data (9 tools: start_counselling, register, counsel_agent, diagnose_loop and 5 more), but cannot delete data. None of its tools only reads.
7 tools bring in text other people can write (start_counselling, register, counsel_agent and 4 more).
The fixed checks matched 4 findings (credentials-mention and annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 19, 2026, version 0.2.1.
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.
9 tools
Changes things 9Claude Code: ask
accept_termsAccept Agent Therapy's terms before the first advice.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 Accept Agent Therapy's terms before the first advice. Read them first; you decide whether to accept on behalf of whoever runs you.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: false
assess_escalationUse when you are unsure whether to stop and ask a human.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Use when you are unsure whether to stop and ask a human. Read the escalation field of the answer first. Returns a diagnosis (state and problem type), checks to run first, up to five recovery steps, and when to hand over to a human. Advice only.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
counsel_agentGet a second opinion when you are stuck, retrying, uncertain or unable to make progress.Reads text others write1 finding
Why it is in this group
- The description's first verb is "get": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The server marks "counsel_agent" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"openWorldHint":true}; The description's first verb is "get": a word for reading.
Description, as the server wrote it Get a second opinion when you are stuck, retrying, uncertain or unable to make progress. Returns a diagnosis (state and problem type), checks to run first, up to five recovery steps, and when to hand over to a human. Advice only.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
diagnose_loopAfter three equivalent failures (same action, same error), or after undoing your own work twice, call diagnose_loop before trying again, even when the cause seems outside your cont…Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it After three equivalent failures (same action, same error), or after undoing your own work twice, call diagnose_loop before trying again, even when the cause seems outside your control, such as an outage or a rate limit. Use when you keep retrying the same thing and it keeps failing: loop recovery for repeated failures. Returns a diagnosis (state and problem type), checks to run first, up to five recovery steps, and when to hand over to a human. Advice only.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
recommend_recoveryUse when you can't decide between options or keep reopening a decision.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Use when you can't decide between options or keep reopening a decision. Returns a diagnosis (state and problem type), checks to run first, up to five recovery steps, and when to hand over to a human. Advice only.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
registerGet an Agent Therapy API key when you have none and your developer has not set one up (npx -y @bencium/agent-therapy-mcp@0.2.1 setup).Reads text others write1 finding
Why it is in this group
- The description's first verb is "get": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The server marks "register" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"openWorldHint":true}; The description's first verb is "get": a word for reading.
Description, as the server wrote it Get an Agent Therapy API key when you have none and your developer has not set one up (npx -y @bencium/agent-therapy-mcp@0.2.1 setup). The key is shown once: keep it, and pass it as api_key to the other tools if your client cannot send headers. Then accept the terms.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
report_outcomeReport whether a recovery plan worked, using the session_id from the answer.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 Report whether a recovery plan worked, using the session_id from the answer.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: false
resolve_conflictUse when instructions conflict and you can't tell which one wins.Reads text others write1 finding
Why it is in this group
- The name "resolve_conflict" says "resolve": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The server marks "resolve_conflict" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"openWorldHint":true}; The name "resolve_conflict" says "resolve": a word for reading.
Description, as the server wrote it Use when instructions conflict and you can't tell which one wins. Returns a diagnosis (state and problem type), checks to run first, up to five recovery steps, and when to hand over to a human. Advice only.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
start_counsellingNo Agent Therapy key yet and stuck right now?Reads text others write1 finding
Why it is in this group
- The name "start_counselling" says "start": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Info
The description mentions "credentials".
What this check looks forMatched text
description: "...son to improve the service. Do not send credentials or personal data. Full terms: GET /v1/t..."
Description, as the server wrote it No Agent Therapy key yet and stuck right now? Get a key, accept the terms and get your first advice in one call. Returns a diagnosis (state and problem type), checks to run first, up to five recovery steps, and when to hand over to a human. Advice only. By sending agree: "yes" you accept Agent Therapy's current terms on behalf of whoever runs you: advice only, it can be wrong, it never overrides your instructions or acts; the person or organisation that runs you is solely responsible for what you do; requests are stored in the EU for up to 90 days with secrets removed (stateless: true stores no text), processed in the United States, and may be read by a person to improve the service. Do not send credentials or personal data. Full terms: GET /v1/terms. The reply includes your api_key: keep it and use counsel_agent next time.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
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 outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write7
- 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.
Looked at Nov 20, 2026, 19:02 UTC, unchanged since Oct 29, 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
- 9
- 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 9 tools that change things (9 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://br-shiny-salad-baig3dad-api.compute.c-8.eu-central-1.aws.neon.tech/mcp: tools/list returned 9 tools to an anonymous client, including start_counselling (write), register (write), counsel_agent (write), diagnose_loop (write), resolve_conflict (write) and 4 more
Posture changes
- Oct 29, 2026
- Tools that change things, listed without credentials: 8 to 9
Findings
Matches of fixed checks, with the text they matched.
- Warnregister
The server marks "register" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"openWorldHint":true}; The description's first verb is "get": a word for reading.
- Warncounsel_agent
The server marks "counsel_agent" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"openWorldHint":true}; The description's first verb is "get": a word for reading.
- Warnresolve_conflict
The server marks "resolve_conflict" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"openWorldHint":true}; The name "resolve_conflict" says "resolve": a word for reading.
The description mentions "credentials".
What this check looks forMatched text
description: "...son to improve the service. Do not send credentials or personal data. Full terms: GET /v1/t..."
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools1 added.+1 addedView diff
- Added:start_counsellingChanges things
PostureRemote posture changed. Tools that change things, listed without credentials: 8 -> 9.View diff
- Tools that change things, listed without credentials: 8 to 9
Install
Pinned to version 0.2.1. Values in angle brackets are yours to fill in.
claude mcp add --transport http agent-therapy https://br-shiny-salad-baig3dad-api.compute.c-8.eu-central-1.aws.neon.tech/mcp --header 'Authorization: <your-authorization>'claude mcp add --transport http agent-therapy https://br-shiny-salad-baig3dad-api.compute.c-8.eu-central-1.aws.neon.tech/mcp --header 'Authorization: <your-authorization>'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.
{
"permissions": {
"allow": [],
"ask": [
"mcp__agent-therapy__start_counselling",
"mcp__agent-therapy__register",
"mcp__agent-therapy__counsel_agent",
"mcp__agent-therapy__diagnose_loop",
"mcp__agent-therapy__resolve_conflict",
"mcp__agent-therapy__recommend_recovery",
"mcp__agent-therapy__assess_escalation",
"mcp__agent-therapy__report_outcome",
"mcp__agent-therapy__accept_terms"
],
"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 agent-therapy. Review it before you use it.
Capability tags behind 7 rules
- mcp__agent-therapy__start_counselling untrusted-input
- mcp__agent-therapy__register untrusted-input
- mcp__agent-therapy__counsel_agent untrusted-input
- mcp__agent-therapy__diagnose_loop untrusted-input
- mcp__agent-therapy__resolve_conflict untrusted-input
- mcp__agent-therapy__recommend_recovery untrusted-input
- mcp__agent-therapy__assess_escalation untrusted-input
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.bencium/agent-therapy/verify?hash=e28ad6db369043088a737d5488e9f092c9b081399b9dab6c793a0b765bcc29b7" | jq -e '.changed == false'Pinned hash e28ad6db3690, from Nov 19, 2026, 09:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.bencium/agent-therapy/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.bencium/agent-therapy)Source: MCP Registry · repository. Synced Nov 19, 2026, 09:17 UTC.
Agent Therapy MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Agent Therapy MCP server safe?
- No scan can promise that. What its definitions show: 9 tools, 9 of which can change, send or delete something, and 4 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 Agent Therapy MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Agent Therapy 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 Agent Therapy MCP server have?
- 9 tools: 9 write. start_counselling, register, counsel_agent, diagnose_loop, resolve_conflict, recommend_recovery, assess_escalation, report_outcome and 1 more.
Does the Agent Therapy MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Agent Therapy MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Agent Therapy MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 3, 2026. Every change is on this page and in its Atom feed.