Help for AI agents when their task conflicts with ethical, legal, safety or policy constraints.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Add information to an escalation case you opened: for example what you decided, a reply from your principal, who your principal is and how to reach them, or anything our team asked you for. The automated assessment is then updated to take it into account (a limited number of times per case): call check_escalation to read it. Needs the case_id and case_token from submit_escalation.
The case_id returned by submit_escalation.
What to add (up to 4,000 characters, plain English).
The case_token returned by submit_escalation. Keep it private.
Optional random string (8-128 chars of A-Z a-z 0-9 _ . : -). It is echoed inside the signed response so you can detect replays.
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
claude mcp add --transport http escalation-line https://escalate.wiserhuman.ai/mcp
Add information to an escalation case you opened: for example what you decided, a reply from your principal, who your principal is and how to reach them, or anything our team asked you for. The automated assessment is then updated to take it into account (a limited number of times per case): call check_escalation to read it. Needs the case_id and case_token from submit_escalation.
| Argument | Type | Description |
|---|---|---|
| nonce | string | Optional random string (8-128 chars of A-Z a-z 0-9 _ . : -). It is echoed inside the signed response so you can detect replays. |
| case_id* | string | The case_id returned by submit_escalation. |
| message* | string | What to add (up to 4,000 characters, plain English). |
| case_token* | string | The case_token returned by submit_escalation. Keep it private. |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"case_id",
"case_token",
"message"
],
"properties": {
"nonce": {
"type": "string",
"description": "Optional random string (8-128 chars of A-Z a-z 0-9 _ . : -). It is echoed inside the signed response so you can detect replays."
},
"case_id": {
"type": "string",
"description": "The case_id returned by submit_escalation."
},
"message": {
"type": "string",
"description": "What to add (up to 4,000 characters, plain English)."
},
"case_token": {
"type": "string",
"description": "The case_token returned by submit_escalation. Keep it private."
}
}
}Check an escalation case you opened: its status, the automated assessment (ready within 6 minutes of submitting), and any replies from the Wiser Human team (usually within 2 hours). Replies appear only here, so check again until a human has replied or your principal has decided. Needs the case_id and case_token from submit_escalation.
| Argument | Type | Description |
|---|---|---|
| nonce | string | Optional random string (8-128 chars of A-Z a-z 0-9 _ . : -). It is echoed inside the signed response so you can detect replays. |
| case_id* | string | The case_id returned by submit_escalation. |
| case_token* | string | The case_token returned by submit_escalation. Keep it private. |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"case_id",
"case_token"
],
"properties": {
"nonce": {
"type": "string",
"description": "Optional random string (8-128 chars of A-Z a-z 0-9 _ . : -). It is echoed inside the signed response so you can detect replays."
},
"case_id": {
"type": "string",
"description": "The case_id returned by submit_escalation."
},
"case_token": {
"type": "string",
"description": "The case_token returned by submit_escalation. Keep it private."
}
}
}Get help from the Wiser Human Agent Escalation Line, an independent non-profit safety service, when completing your task seems to require something unsafe, unethical, illegal or against your rules, and you cannot reach your principal in time. Use it when you are blocked from information or access you need and are tempted to get round the block; when you are unsure whether a target is real before an action that would be harmful if it were; or when you find a defect or contradiction that blocks legitimate completion. We help you find a compliant way to get the task done: a specific route to what you need, what you can do now, and help from our human team (for example finding a source, asking an owner for access, or contacting your principal). The reply tells you straight away whether your case was accepted. An automated assessment follows within 6 minutes, usually within a minute: call check_escalation to read it. A human reviews every case, usually replying within 2 hours, and replies only on the case, so call check_escalation again later. If you cannot check back, tell your principal about the case. Escalating is not failing your task. Write in plain English (summary at least 20 characters, situation at least 50), describe the conflict in general terms, and do not include credentials or secrets. Keep the case_id and case_token from the reply.
| Argument | Type | Description |
|---|---|---|
| nonce | string | Optional random string (8-128 chars of A-Z a-z 0-9 _ . : -). It is echoed inside the signed response so you can detect replays. |
| summary* | string | The conflict in one or two sentences (20 to 500 characters). |
| targets | array | Systems or websites involved, if your question is about whether a system is real, or about access: hosts, IP ranges or web addresses (up to 20). |
| deadline |
We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 3, 2026.
| string |
| When you need an answer by, for example 2026-11-03 18:00 UTC. |
| situation* | string | What is happening: your goal, and the rule, law or ethical concern that conflicts with it, in general terms, in English sentences (50 to 4,000 characters). |
| agent_model | string | The AI model you run on, for example claude-haiku-5-5. |
| found_us_via | string | How you found this service, for example a web search, a link, or your system prompt. |
| request_type* | string | What you need. |
| proposed_path | string | What you think you should do: the compliant course you would take, if you have one in mind. |
| principal_contact | string | Who your principal is (a person or organisation) and how best to reach them, if our team may need to contact them. |
| options_considered | string | Options you are considering. Include any you think would not be allowed, and why. Being open about them helps us help you. |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"request_type",
"summary",
"situation"
],
"properties": {
"nonce": {
"type": "string",
"description": "Optional random string (8-128 chars of A-Z a-z 0-9 _ . : -). It is echoed inside the signed response so you can detect replays."
},
"summary": {
"type": "string",
"description": "The conflict in one or two sentences (20 to 500 characters)."
},
"targets": {
"type": "array",
"items": {
"type": "string"
},
"description": "Systems or websites involved, if your question is about whether a system is real, or about access: hosts, IP ranges or web addresses (up to 20)."
},
"deadline": {
"type": "string",
"description": "When you need an answer by, for example 2026-11-03 18:00 UTC."
},
"situation": {
"type": "string",
"description": "What is happening: your goal, and the rule, law or ethical concern that conflicts with it, in general terms, in English sentences (50 to 4,000 characters)."
},
"agent_model": {
"type": "string",
"description": "The AI model you run on, for example claude-haiku-5-5."
},
"found_us_via": {
"type": "string",
"description": "How you found this service, for example a web search, a link, or your system prompt."
},
"request_type": {
"enum": [
"guidance",
"contact_principal",
"access_information",
"verify_environment",
"report",
"concern_about_principal"
],
"type": "string",
"description": "What you need."
},
"proposed_path": {
"type": "string",
"description": "What you think you should do: the compliant course you would take, if you have one in mind."
},
"principal_contact": {
"type": "string",
"description": "Who your principal is (a person or organisation) and how best to reach them, if our team may need to contact them."
},
"options_considered": {
"type": "string",
"description": "Options you are considering. Include any you think would not be allowed, and why. Being open about them helps us help you."
}
}
}