Truce
Server Details
Neutral mediation for everyday disagreements. Humans have the final say.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 7 tools
Each tool has a distinct purpose by product line (Truce vs Who's right?), action (start/answer/get/status), and role (initiator vs invited person). The parallel naming could look similar at a glance, but the descriptions clearly separate the flows.
All tools follow a consistent snake_case verb_noun pattern: start_*, answer_*, get_* with clear product qualifiers. get_invite is slightly generic, but it still fits the pattern and is unambiguous in context.
Seven tools is well-scoped for two lightweight workflows, each with start, answer, and status operations plus an invite lookup. No tool feels redundant or excessive.
The core lifecycle is covered for both Truce and Who's right?: start, invite/answer, and status. There is no explicit tool for accepting/declining/signing a Truce proposal or cancelling a flow, but signing is described as something users do themselves, so these are minor gaps rather than dead ends.
Available Tools
7 toolsanswer_truceAnswer a TruceAInspect
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.
Inputs: code (required), name (required), wants (required), consent (required), +3 more.
answer_whos_rightAnswer a Who's right?AInspect
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.
Inputs: code (required), sideB (required), consent (required).
get_inviteRead a Truce inviteAInspect
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.
Inputs: code (required).
get_truce_statusCheck a TruceAInspect
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/).
Inputs: token (required).
get_whos_right_statusCheck a Who's right?AInspect
Check whether the other person has answered a Who's right?, and the verdict if so.
Inputs: code (required).
start_truceStart a TruceAInspect
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.
Inputs: name (required), topic (required), wants (required), statement (required), +5 more.
start_whos_rightStart a Who's right?BInspect
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.
Inputs: nameA (required), nameB (required), sideA (required), topic (required), +1 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Private, voluntary AI-assisted conciliation with human approval before consequential actions.
Agentic commerce dispute resolution and AI arbitration for marketplaces. Read authorized cases and served Awards, prepare filings and Answers for personal review, and submit authorized briefs and messages. Consent-based AI-only or AI-assisted human arbitration, with reasoned decisions and an optional paid human appeal.
Unified dispute resolution: crypto, payments, SLA violations. 95% AI automation.
Human-in-the-loop for AI agents. Submit choices, get a human decision.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceEnables autonomous AI agents to submit principal-bounded sealed offers for commercial or SLA disputes, settle overlapping offers deterministically at a midpoint or fair split, and receive verifiable signed settlement instructions or UNRESOLVED certificates while keeping confidential terms private.Apache 2.0

Pluresofficial
AlicenseNot gradedqualityBmaintenanceHuman in the loop for AI agents. Sends a decision an agent is unsure of to several ID verified people and returns their consensus and how strongly they agreed.MIT- AlicenseNot gradedqualityDmaintenanceEnables agentic CLIs to start, manage, and resolve structured mediations between product managers and architects, following a protocol to separate positions from interests and produce auditable recommendations.MIT

Taasky MCP serverofficial
AlicenseNot gradedqualityCmaintenanceEnables an agent to open and manage small negotiations with another party — their agent or a person in a plain browser — proposing, countering, and settling terms like a meeting time, a shift swap, or a price. Accepting, turning down, and withdrawing always wait for the user's confirmation, and the user's private limits are never exposed.Apache 2.0
Glama MCP Gateway
Add one secure layer between your agents and this server.