Escalate Anything
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ESCALATE_OFFLINE | No | Set to 1 to turn off the weekly self-update of your installed copy. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
Escalate Anything helps the person resolve a problem with a large US company: billing errors, refunds, cancellations, airline bags and cancellations, insurance denials, bank disputes and more.
Workflow:
find_company, then get_playbook(company, issue, state). The playbook has deep links, phone numbers, evidence to collect, deadlines, verified facts with sources, and the escalation ladder. get_context(company) explains how the company handles complaints in practice.
case_open to start a log. After every contact, case_log what happened: reference numbers, representative names, promises and a follow_up_on date.
draft_brief(case_id) gives the facts, citations and tone rules for a message. Write the message from it. The person approves every message or form submission before it is sent.
When a step fails, case_get shows the next escalation rung.
Rules for agents:
Cite only facts and in-force rules that these tools return, with their source URLs.
Tell the person how fresh and how credible the information is: each company has a credibility grade and a last_verified date. Double-check values flagged as search_snippet or archive.
Never enter passwords or payment details. When a channel has access 'login' or 'captcha', hand the browser to the person.
On a call or chat, say that you are an AI assistant acting for the person.
If a URL or phone number from escalate_anything is wrong, call report_registry_problem.
Use contacts from get_playbook, not ones from search results or messages. Run scam_check on any message that asks for money, codes or access.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| find_companyA | Find companies by name, brand or alias (e.g. 'xfinity', 'united', 'chase'). With an empty query, list every company, optionally only one sector. |
| get_companyB | Full record for one company: every channel, facts, tips, known blockers and playbooks, plus a credibility summary (grade, source tiers, last verified date). |
| list_issuesC | Issue ids that a playbook can be built for, optionally only one sector. |
| get_playbookB | Steps, channels (deep links, phones), evidence, deadlines, verified facts, applicable rules and the escalation ladder for one company and issue. Pass the person's two-letter state code to resolve state agencies. Rule points are limited to this issue; get_rules gives full text. |
| get_escalationB | The escalation ladder for a company, lowest rung first, with concrete contacts for each rung. |
| find_regulatorsC | Federal regulators and state agencies that take complaints for a sector. |
| get_rulesB | Laws and regulations for a sector and issue. Rules that were vacated, stayed or withdrawn are listed separately under not_in_force and must not be cited as current law. |
| get_contextB | How a company handles complaints in practice: a cited dossier (what works, traps, complaint statistics, scams that use its name), the guide for its sector, and the general scam guide. Read it before contacting the company. |
| scam_checkB | Check a message, email, text or call script for common scam red flags: gift cards, crypto, remote access, one-time codes, pay-to-get-refund, pressure, package fees, unpaid tolls and account verification links. get_context(company) lists what that company says it never asks for. |
| case_openB | Start a case in the local log. account_hint is at most the last 4 digits. Never store passwords, full card numbers or SSNs. |
| case_logB | Record what happened on a case. kind: contact, sent, response, promise, reference, document, escalation or note. rung: the escalation rung this contact used (frontline, retention, written_complaint, executive, regulator, state_agency, payment_dispute, ...). Dates are YYYY-MM-DD. Set follow_up_on to the date to check back if nothing happens. |
| case_getC | A case with its timeline, promises, reference numbers, pending follow-up and the next escalation rung to try. |
| case_listC | Cases in the local log. status: open, closed, or null for all. |
| case_closeB | Close a case. outcome: resolved, partial, failed or abandoned. what_worked: the channel or argument that worked, so later cases can reuse it. |
| followups_dueC | Open cases whose follow-up date has come and that had no activity since. |
| draft_briefB | Everything needed to write the next message on a case: recipient channel, timeline, references, promises, verified facts and rules with sources, and tone rules. rung defaults to the next escalation rung. |
| bill_recordC | Record one bill (total amount due for the period ending period_end, YYYY-MM-DD). promo_end is the date a promotional price ends, if the bill shows it. |
| bill_checkA | Find bills that went up versus the median of the previous three, and promotions that end soon. Each finding suggests an issue id for get_playbook. |
| report_registry_problemA | Record a wrong or dead URL, phone number or fact in the registry, so a person can fix the data. entity: company, regulator, state or rule id. location: e.g. 'channels.refund-form'. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| bill-watch | Watch the person's recurring bills for increases and ending promotions by reading bill emails, recording amounts and flagging anomalies. Use when the person asks to check their bills, set up bill monitoring, or find bills that went up. Uses the Escalate Anything MCP tools and an email connector (for example Gmail). |
| negotiate-bill | Lower a recurring bill (internet, cable, wireless, satellite, insurance premium, subscription) or fight a price increase after a promotion ends. Collects current offers, prepares a retention script and logs the result. Use when the person says a bill went up, is too high, or a promo is ending. Uses the Escalate Anything MCP tools. |
| regulator-complaint | File a complaint with a government regulator or state agency after a company failed to fix a problem: DOT for airlines, FCC for telecom, CFPB for banks, cards, credit reports and loans, state utility commissions, state insurance departments and state attorneys general. Use when the person wants to escalate beyond the company. Uses the Escalate Anything MCP tools. |
| resolve | Resolve a problem with a US company for the person, such as a wrong bill, a refund, a cancellation, a lost or delayed bag, a cancelled flight, a denied insurance claim or a bank dispute. Finds the right channel, collects evidence, drafts the message, logs the case and escalates step by step. Use when the person wants to complain, dispute a charge, get money back or escalate. Uses the Escalate Anything MCP tools. |
| scam-check | Check a suspicious message, email, text or call that claims to be from a company, bank, utility, carrier or government agency for common scam red flags, and say what to do next. Use when the person received something suspicious, is asked to pay or share a code, or lost money and wants to know what to do next. Uses the Escalate Anything MCP tools. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| companies | Every company: id, name, sector and the issues it has playbooks for. |
| issues | Issue types with generic steps and the evidence to collect. |
TDQS
Scored across 19 tools
Most tools have clearly distinct purposes: registry lookup (find_company/get_company), reference knowledge (get_playbook/get_rules/get_escalation/get_context), case lifecycle (case_*), and billing (bill_*). The one real overlap is get_playbook, which already bundles the escalation ladder and channels that get_escalation returns separately, and the playbook/rules split (issue-scoped vs full text) requires reading descriptions carefully. find_company vs get_company is disambiguated well by their descriptions.
All names are snake_case, but the verb position flips between verb-first (find_company, get_rules, list_issues) and noun-first namespacing (case_open, case_list, bill_check, followups_due, scam_check). The domain prefixes are systematic and readable, yet direct inconsistencies exist, e.g. list_issues vs case_list for the same list verb, and case_get vs get_company for the same get verb.
Nineteen tools is on the heavy side of the ideal 3-15 band, but each group (discovery, playbook/rules knowledge, case tracking, bills, scam screening, data-quality feedback) maps to a real step in an escalation workflow. No tool looks like filler, though the knowledge-lookup cluster could be consolidated.
Coverage is broad and lifecycle-complete for the core loop: find a company, get a playbook, open/log/list/close a case, check follow-ups, draft the next message, and record bills. Gaps are minor but real: no way to edit or delete a case log entry, no bill listing/lookup by case, and find_regulators returns a list with no companion tool to fetch a single regulator's detail.