A
licenseNot graded
qualityD
maintenanceEnables AI assistants to manage customer support for a fictional candle shop, including order lookup, customer file access, and safe refund processing with server-side safety rules.
MIT
Desk by Ouroboros Apps
Server Details
Customer support answers, refund rules, and escalation limits for AI assistants
If you are the author of this connector, you can claim ownership by verifying the domain or GitHub account it belongs to. Claimed connector authors can inspect health checks, view analytics, and manage their listing.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- LAHutchins91/desk-mcp
- GitHub Stars
- 0
- Server Listing
- Desk by Ouroboros Apps
- ChatGPT
- –
- Claude
- –
TDQS
A3.9/5.0
Scored across 13 tools
Disambiguation4/5
Most tools target a distinct resource+action, and the split between read tools (list_*, get_desk_context, search_approved_answers) and decision tools (evaluate_*) is clear. The main risk is evaluate_commitment vs evaluate_escalation, which sound similar, but descriptions explicitly separate wording approval from channel permission.
Naming Consistency5/5
Every tool follows a clean verb_noun snake_case pattern (create_/evaluate_/get_/list_/save_/search_). No mixed conventions or style drift across the 13 tools.
Tool Count5/5
13 tools is well within the ideal 3-15 range and the set is logically partitioned into read, save, and evaluate operations. Each tool maps to a concrete action with no filler.
Completeness4/5
Coverage is strong: desks are created/listed, and answers, commitments, escalation limits, and refund rules each have list/save (and search/evaluate) counterparts. Minor gaps exist—no update/delete or retire operation for desks, and no explicit delete for saved rules—but core policy lifecycle is covered.
Available Tools
13 toolscreate_support_deskcreate support deskBIdempotentInspect
Create a support desk when the user asks for a new policy home. Does not approve answers, refunds, features, or timelines.
Inputs: name (required), description. Returns: data
evaluate_commitmentevaluate commitmentARead-onlyIdempotentInspect
Decide whether a proposed refund, feature, or timeline is in the approved set. REFUSED means do not say it, do not invent a substitute, and draft for human review instead of promising the customer. APPROVED means sayOnly is the only permitted wording. Pass channel to also enforce the escalation limit.
Inputs: kind (required), deskId (required), proposal (required), channel. Returns: data
evaluate_escalationevaluate escalationARead-onlyIdempotentInspect
Decide whether this channel may escalate or may promise a refund, feature, or timeline. REFUSED means do not escalate, do not invent a tier, and draft for human review instead of promising the customer. Permission to promise still requires evaluate_commitment for the exact wording.
Inputs: action (required), deskId (required), channel (required), targetTier. Returns: data
get_desk_contextget desk contextARead-onlyIdempotentInspect
Retrieve selected approved answers for a customer question, plus the desk's approved refund rules, commitments, and escalation limits. This is evidence, not permission. A missing or RETIRED answer is not an invitation to invent one. Call evaluate_commitment before promising a refund, feature, or timeline. If tools fail or return gaps or REFUSED, draft for human review instead of promising the customer.
Inputs: deskId (required), question (required), limit. Returns: data
list_approved_commitmentslist approved commitmentsBRead-onlyIdempotentInspect
Read approved feature and timeline statements. Listing them does not approve a different promise. Call evaluate_commitment with the exact wording before saying one.
Inputs: deskId (required), kind, includeRetired. Returns: data
list_escalation_limitslist escalation limitsBRead-onlyIdempotentInspect
Read escalation limits. A channel with no APPROVED limit cannot promise a refund, feature, or timeline and cannot be given an invented escalation path.
Inputs: deskId (required), includeRetired. Returns: data
list_refund_ruleslist refund rulesARead-onlyIdempotentInspect
Read refund rules on a desk. Only APPROVED rules can authorize wording, and only through evaluate_commitment. Do not treat this list as permission to invent a refund.
Inputs: deskId (required), includeRetired. Returns: data
list_support_deskslist support desksBRead-onlyIdempotentInspect
List this team's support desks. Use the returned id. Do not guess a desk.
Inputs: offset. Returns: data
save_approved_answersave approved answerADestructiveIdempotentInspect
Store or revise an answer the user has explicitly approved. Identical retries keep the same revision. A changed answer requires expectedRevision from a previous read.
Inputs: topic (required), answer (required), deskId (required), question (required), +2 more. Returns: data
save_approved_commitmentsave approved commitmentADestructiveIdempotentInspect
Store a feature or timeline statement the user has explicitly approved. The statement is the only wording that can later pass evaluate_commitment. Do not save a date or a feature the user did not approve.
Inputs: kind (required), name (required), deskId (required), statement (required), +2 more. Returns: data
save_escalation_limitsave escalation limitADestructiveIdempotentInspect
Store the escalation limit the user has explicitly approved for one channel. maxTier must be on tierLadder. Promise flags default closed unless the user sets them true. A limit does not itself approve refund, feature, or timeline wording.
Inputs: name (required), deskId (required), channel (required), maxTier (required), +7 more. Returns: data
save_refund_rulesave refund ruleADestructiveIdempotentInspect
Store a refund rule the user has explicitly approved. matchTerms must name a specific situation. The word refund alone is not a rule. remedy is the only wording that may later be approved. decision ALLOW grants that wording. decision DENY refuses a refund and records the denial script.
Inputs: name (required), deskId (required), remedy (required), decision (required), +4 more. Returns: data
search_approved_answerssearch approved answersARead-onlyIdempotentInspect
Look up approved answers by topic, question, or answer text. An empty result means there is no approved answer. Draft for human review; do not invent one or promise the customer. Page with offset.
Inputs: deskId (required), query, offset, includeRetired. Returns: data
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
AI customer service: set up an AI support agent, search knowledge, look up orders, answer customers.
AI support employee for any website: learns the site, answers visitors by chat and voice.
Work your Zono Support help desk from an AI client: tickets, customers, purchases and knowledge.
Customer feedback for your AI assistant: CSAT, NPS and CES scores, response search, AI themes.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to manage a customer-support inbox with guardrails, including replying safely, handling escalations, and leveraging upsell opportunities for e-commerce stores.MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to independently investigate and resolve e-commerce order issues, particularly refund processing, with tools for order search, refund eligibility checks, and safe refund execution.MIT
- AlicenseAqualityCmaintenanceEnables AI assistants to answer customer questions from a shop's own product catalog, FAQs, and policy documents, with read-only access and cited answers.5MIT
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd
Glama MCP Gateway
Add one secure layer between your agents and this server.