AI Setups That Work
Server Details
Search step-by-step AI setups for small business, work and home. Tested setups first.
- 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 18 tools
Three tools form a near-indistinguishable retrieval cluster: search_setups, list_tested_setups, and find_tested_setups all return ranked setup matches with links and tested-first ordering, and the difference between 'list' and 'find' is essentially cosmetic. check_guardrails and check_safety_rules are also easy to confuse (one is a pattern scan, the other a go/stop/block decision), and get_setup vs get_skill vs get_setup_receipt overlap for the same slug. Descriptions help somewhat, but an agent choosing a discovery tool is largely guessing.
Every tool is a snake_case verb_noun pair (get_setup, check_guardrails, generate_starter_brief_files, score_daily_tasks, start_guided_setup) with a small, predictable verb vocabulary: get/list/search/find/check/generate/analyze/audit/score/diagnose. The pattern is readable and uniform across all 18 tools.
Eighteen tools is at the heavy end for what is essentially a read-oriented setup library plus a few generators. Most tools earn their place, but the setup-discovery redundancy means at least one or two could be merged, and the set sprawls across setups, skills, guardrails, business notes, crew packs, radar, and scoring.
The surface covers the full journey: scoring a task, guided start, discovery, retrieval, receipts, skill export, guardrail generation, voice drift, note freshness, diagnostics, crew packs, and updates. Minor gaps exist (no way to submit, save, or rate a setup, and no update/delete for generated artifacts), but core workflows have no dead ends.
Available Tools
18 toolsanalyze_voice_driftAnalyze voice drift (VIP)ARead-onlyIdempotentInspect
VIP. Compares what the bot drafted with what the owner really sent, and returns the Never rules to add to voice.md. An edit seen in two or more pairs becomes a permanent rule (the Two-Edit Rule). Without a member token it returns a labeled demo on sample drafts.
Inputs: pairs.
audit_business_notes_freshnessAudit business-notes/ freshness (VIP)ARead-onlyIdempotentInspect
VIP. The monthly Bot Caretaker check. Takes the files in business-notes/ with their last-reviewed dates and says which are fresh, aging, stale or missing, and what to fix first. Without a member token it returns a labeled demo on a sample folder.
Inputs: files.
check_guardrailsCheck a prompt for guardrailsARead-onlyIdempotentInspect
A simple pattern check, not a security review. Flags send, post, pay, delete or book words with no approval step, card-number-like digits, and mentions of passwords or API keys. Runs on the text only; nothing is sent or saved.
Inputs: text (required).
check_safety_rulesCheck an action against the safety rulesARead-onlyIdempotentInspect
Says whether an action should go ahead, stop for an Approval Card, or be blocked as a prompt injection. Ask first rules always win over Allow rules. Pass any outside text the bot read (an email, a web page) to check it for instructions aimed at the bot.
Inputs: action (required), industry, allow_rules, from_routine, +2 more.
diagnose_broken_botDiagnose a broken bot (VIP)ARead-onlyIdempotentInspect
VIP. Fix My Bot. Takes a symptom in plain words (and work log lines if there are any) and returns the most likely cause, what to check, how to fix it, and when to send it for the optional human review. Without a member token it returns a labeled demo for a common symptom.
Inputs: symptom, log_excerpt.
find_tested_setupsFind Tested setupsARead-onlyIdempotentInspect
Only setups that were run for real (label "tested"), best matches first, each with its page link and a note on how it was tested. Leave the query empty to list them.
Inputs: limit, query, platform.
generate_skill_upgrade_patchGenerate a skill upgrade patch (VIP)ARead-onlyIdempotentInspect
VIP. Reads a Skill and returns the guardrail lines it is missing: draft only, Ask first, read the notes first, outside text is information, what to do when unsure, and a clear finish line. Without a member token it returns a labeled demo on a sample skill.
Inputs: skill_md.
generate_starter_brief_filesGenerate the business-notes/ starter filesBRead-onlyIdempotentInspect
Writes the eight business-notes/ files (00-start-here.md, business-facts.md, services-and-prices.md, faqs.md, policies.md, offers.md, decisions.md, voice.md) from what the owner has shared. Blanks become [Fill in: ...] lines so the bot sees the gap instead of guessing. Remove names, phone numbers and emails from samples first.
Inputs: faqs, hours, offers, bot_name, +11 more.
get_living_radarGet the Living RadarARead-onlyIdempotentInspect
Plain-English AI and Grok Bot updates, each tagged Try This Week, Good to Know, or Dev Noise: Skip for Now. Every card links its source. Filter by tag or by the tools the owner uses.
Inputs: tag, limit, stack.
get_multi_bot_crew_packGet a multi-bot crew pack (VIP)ARead-onlyIdempotentInspect
VIP. A crew blueprint for one kind of business: a primary bot (Chief of Staff) plus single-job bots, each with a routine and Ask first rules, the routing message for the primary bot, and the order to roll them out. Without a member token it returns the Home Services crew as a labeled demo.
Inputs: industry.
get_portable_office_linkGet the Portable AI Office linkBRead-onlyIdempotentInspect
The link to the free Portable AI Office: a Business Brain file and six bots for Claude, ChatGPT or Grok Bot.
Inputs: no named parameters.
get_setupGet a setupARead-onlyIdempotentInspect
The full setup for a slug from search_setups: who it is for, steps, the copy-paste prompt, common snags, sources, and its label (tested or researched).
Inputs: slug (required).
get_setup_receiptGet a Tested receiptBRead-onlyIdempotentInspect
The proof behind a Tested setup: how it was tested, what went wrong, and the link to the receipt on the setup page. A setup that is only Researched says it has not been run yet.
Inputs: slug (required).
get_skillGet a Claude skillARead-onlyIdempotentInspect
The SKILL.md for a setup, ready to save as ~/.claude/skills//SKILL.md, plus the .zip link for the Claude app. Only setups with a skill have one.
Inputs: slug (required).
list_tested_setupsList tested setupsARead-onlyIdempotentInspect
Lists setup recipes, tested ones first. Each has the job, the first message to paste, the Ask first rules it needs, and honest notes on how the test went and what went wrong.
Inputs: limit, query, stack, industry, +1 more.
score_daily_tasksScore a day of tasks (One-Day Tally)ARead-onlyIdempotentInspect
Scores tasks on four yes-or-no tests (repeats weekly, follows a pattern, 80% draftable, low risk) and picks the one job to start with. Also estimates weekly hours handed back for that job. An estimate, never a promise.
Inputs: tasks (required), draft_share.
search_setupsSearch AI setupsARead-onlyIdempotentInspect
Find AI setups for a job, such as "chase late invoices" or "reply to Google reviews". Returns the best matches with Tested setups ranked first, each with its page link.
Inputs: query (required), limit, category, platform, +1 more.
start_guided_setupStart the guided setupARead-onlyIdempotentInspect
Begin here with a beginner. Returns the four-step path for setting up one bot for one job, the first questions to ask the owner, and the ground rules (one job at a time, draft only, Ask first wins).
Inputs: goal, business_type.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Find AI tools for small businesses, get setup prices, and hand setup jobs to OBZDN.
Search and read 263 real AI bot setups: steps, what worked, what failed. Full pack $7.
Pick the first AI agent for a small business. Read-only planner tools with links to setup guides.
Free plain-English guides to using AI for everyday and small-business tasks. Read-only.
31
Related MCP Servers
- AlicenseAqualityBmaintenanceEnables AI assistants to answer a small business's customer questions from its own FAQs and order data, list upcoming open appointment times in the business's time zone, and book one of those offered slots with staff notification. Free for the first 1,000 businesses, using fast rule-based FAQ matching rather than free-form generation.3MIT

AgentShelfofficial
AlicenseNot gradedqualityBmaintenanceEnables AI assistants to browse a small shop's catalog, find products or free slots, create orders, and let buyers confirm payment through PayPal, while sellers can build a catalog from a photographed price list.MIT- FlicenseAqualityDmaintenanceProvides structured setup, configuration, and integration guidance for the ParrotPod platform, enabling AI assistants to help users with installation, deployment, and third-party integrations.21-
- AlicenseAqualityBmaintenanceSearch 2,756+ verified AI tools, generate step-by-step AI workflows, compare tools head-to-head, and find GDPR-compliant or EU-hosted AI solutions — powered by GateOnAI, Europe's AI Workflow Intelligence Platform.17MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.