Neutral mediation for everyday disagreements. Humans have the final say.
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.
For the agent of the invited person: give their side of the Truce, in private, so the neutral mediator can propose something fair. Only with their explicit consent to the exact words. They still read the proposal and sign themselves.
The code at the end of the invite link.
Your user's first name.
What your user would like to happen.
Must be true: your user asked you to answer and agreed to these words.
Your user's side, in their words.
Optional: your user's email for updates.
Optional, private: the least your user could accept. Never shown to the other side.
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.
Run in a terminal
claude mcp add --transport http truce https://trucehq.com/mcp
For the agent of the invited person: give their side of the Truce, in private, so the neutral mediator can propose something fair. Only with their explicit consent to the exact words. They still read the proposal and sign themselves.
| Argument | Type | Description |
|---|---|---|
| code* | string | The code at the end of the invite link. |
| name* | string | Your user's first name. |
| string | Optional: your user's email for updates. | |
| floor | string | Optional, private: the least your user could accept. Never shown to the other side. |
| wants* | string | What your user would like to happen. |
| consent* | boolean | Must be true: your user asked you to answer and agreed to these words. |
| statement* | string | Your user's side, in their words. |
{
"type": "object",
"required": [
"code",
"name",
"statement",
"wants",
"consent"
],
"properties": {
"code": {
"type": "string",
"description": "The code at the end of the invite link."
},
"name": {
"type": "string",
"description": "Your user's first name."
},
"email": {
"type": "string",
"description": "Optional: your user's email for updates."
},
"floor": {
"type": "string",
"description": "Optional, private: the least your user could accept. Never shown to the other side."
},
"wants": {
"type": "string",
"description": "What your user would like to happen."
},
"consent": {
"type": "boolean",
"description": "Must be true: your user asked you to answer and agreed to these words."
},
"statement": {
"type": "string",
"description": "Your user's side, in their words."
}
}
}For the agent of the other person in a Who's right? (trucehq.com/whos-right/CODE): give their side, with their consent. Returns the neutral, good-humoured verdict.
| Argument | Type | Description |
|---|---|---|
| code* | string | The code at the end of the link. |
| sideB* | string | Your user's side, in a few sentences. |
| consent* | boolean | Must be true: your user asked you to answer and agreed to these words. |
{
"type": "object",
"required": [
"code",
"sideB",
"consent"
],
"properties": {
"code": {
"type": "string",
"description": "The code at the end of the link."
},
"sideB": {
"type": "string",
"description": "Your user's side, in a few sentences."
},
"consent": {
"type": "boolean",
"description": "Must be true: your user asked you to answer and agreed to these words."
}
}
}For the agent of someone who received a Truce invite link (trucehq.com/claim/CODE): see who invited them, what about, and whether it is still open. Read-only.
| Argument | Type | Description |
|---|---|---|
| code* | string | The code at the end of the invite link. |
{
"type": "object",
"required": [
"code"
],
"properties": {
"code": {
"type": "string",
"description": "The code at the end of the invite link."
}
}
}Check a Truce your user started: whether the other side joined, the proposal, and whether both signed. Needs the private token from the private_url (the part after /t/).
| Argument | Type | Description |
|---|---|---|
| token* | string | The private token from private_url. |
{
"type": "object",
"required": [
"token"
],
"properties": {
"token": {
"type": "string",
"description": "The private token from private_url."
}
}
}Check whether the other person has answered a Who's right?, and the verdict if so.
| Argument | Type | Description |
|---|---|---|
| code* | string | The code at the end of invite_url. |
{
"type": "object",
"required": [
"code"
],
"properties": {
"code": {
"type": "string",
"description": "The code at the end of invite_url."
}
}
}Start a Truce (neutral, private mediation) for your user about a real disagreement. Returns an invite link for your user to send to the other person, and a private link for your user. Free unless money is involved.
| Argument | Type | Description |
|---|---|---|
| name* | string | Your user's first name. |
| string | Optional: your user's email for updates. | |
| floor | string | Optional, private: the least your user could accept. Never shown to the other side. |
| olive | string | Optional short, kind note to the other person. |
| topic* | string | What the disagreement is about, in a few neutral words. |
| wants* | string | What your user would like to happen. |
| category | string | Optional: deposit, invoice, flatmates, neighbours, friends, business, family or other. |
| otherName | string | The other person's first name. |
| statement* | string |
Start a free, friendly 'Who's right?' for a light everyday argument. Your user gives their side; the other person gives theirs in private; both get a neutral, good-humoured verdict and a fair middle ground.
| Argument | Type | Description |
|---|---|---|
| string | Optional: your user's email. | |
| nameA* | string | Your user's first name. |
| nameB* | string | The other person's first name. |
| sideA* | string | Your user's side, in a few sentences. |
| topic* | string | What the argument is about. |
{
"type": "object",
"required": [
"topic",
"nameA",
"nameB",
"sideA"
],
"properties": {
"email": {
"type": "string",
"description": "Optional: your user's email."
},
"nameA": {
"type": "string",
"description": "Your user's first name."
},
"nameB": {
"type": "string",
"description": "The other person's first name."
},
"sideA": {
"type": "string",
"description": "Your user's side, in a few sentences."
},
"topic": {
"type": "string",
"description": "What the argument is about."
}
}
}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 21, 2026.
Takes a password, API key or token as an argument, so the secret passes through the model's context and chat logs.
Fix: Read credentials from the server's own configuration (environment, OAuth) instead of a tool argument.
No readOnlyHint / destructiveHint annotations, so clients can't tell a read from a write without asking.
Fix: Add annotations to each tool, e.g. { readOnlyHint: true } for tools that only read.
| Your user's side, in their words. |
{
"type": "object",
"required": [
"topic",
"name",
"statement",
"wants"
],
"properties": {
"name": {
"type": "string",
"description": "Your user's first name."
},
"email": {
"type": "string",
"description": "Optional: your user's email for updates."
},
"floor": {
"type": "string",
"description": "Optional, private: the least your user could accept. Never shown to the other side."
},
"olive": {
"type": "string",
"description": "Optional short, kind note to the other person."
},
"topic": {
"type": "string",
"description": "What the disagreement is about, in a few neutral words."
},
"wants": {
"type": "string",
"description": "What your user would like to happen."
},
"category": {
"type": "string",
"description": "Optional: deposit, invoice, flatmates, neighbours, friends, business, family or other."
},
"otherName": {
"type": "string",
"description": "The other person's first name."
},
"statement": {
"type": "string",
"description": "Your user's side, in their words."
}
}
}