Tulip (BYOK)
Read your Tulip frontline operations setup: stations, station groups, interfaces, roles, user groups, app groups, machine types and tables with your own API token
OKR templates with computed quality checks — measurability, deadlines, SMART criteria
Unify Dynamics LLC
Real questions, and the tools your agent calls to answer them.
list_goal_areasgenerate_okr_templateokr_quality_checkobjective_quality_checksmart_scoreokr_examplescascade_guidanceokr_glossaryscoring_scale_explainerreview_cadence_planOkrframe generates OKR templates and computes quality checks on drafts rather than just describing the framework. generate_okr_template produces an Objective + N Key Result template for a goal area (sales, engineering, marketing, customer_success, product, hr, finance, operations, personal_development). okr_quality_check computes whether a draft Key Result has a number, a deadline/time-bound phrase, and reads like an outcome rather than a task. objective_quality_check flags the opposite pattern in a draft Objective. smart_score computes Specific/Measurable/Time-bound from the text and flags Achievable/Relevant as needing human judgment. okr_examples gives an original example Objective and 3 Key Results per goal area. cascade_guidance explains company/team/individual cascading; okr_glossary defines OKR terms; scoring_scale_explainer covers the 0.0-1.0 scoring convention and stretch-vs-committed grading. review_cadence_plan computes checkpoint weeks and calendar dates across an OKR cycle. Keyless; fully local; nothing stored.
Sources: Quality checks are computed heuristics (regex/keyword pattern matching) run locally on the text supplied; example OKRs and reference content are original compositions describing widely-published OKR practice; fully local, zero upstream calls
The publisher, Unify Dynamics LLC, states that tool inputs are processed in memory and not retained.
10 tools, grouped by job. Every one is read-only or compute-only.
https://okrframe.connectorbay.com/mcpRead your Tulip frontline operations setup: stations, station groups, interfaces, roles, user groups, app groups, machine types and tables with your own API token
Read your Sesame HR company setup: offices, departments, roles, absence types, holiday calendars, contract types and open vacancies with your own API token
Read your PartsBox electronics inventory: parts, stock, storage locations, lots, projects and BOMs, builds and purchase orders with your own PartsBox API key
Read your Zulip Cloud organization's users, channels, topics, subscriptions and user groups with your own bot or user API key (never message text)
Read your Stoat (formerly Revolt) chat servers, members, channels, roles, emoji and invites with your own bot token (never message text)
Read your matrix.org account, joined rooms, room names, topics, members and the public room directory with your own access token
"Give me an OKR template for engineering", "is this a good key result", "score this KR against SMART criteria", "how should OKRs cascade from company to team" — a template builder that actually checks your draft, not just a form.
generate_okr_template produces an Objective placeholder plus N Key Result placeholders for a goal area (sales,
engineering, marketing, customer success, product, HR, finance, operations, personal development), each with
guidance on what makes it good. okr_quality_check runs computed checks on a draft Key Result: does it contain a
number, a deadline or time-bound phrase, and does its first verb read like a measurable outcome rather than a task
("increase" versus "attend")? objective_quality_check checks a draft Objective for the opposite pattern — numbers
that probably belong in a Key Result instead, or a phrase that's run on too long. smart_score scores a Key Result
against SMART criteria: Specific, Measurable and Time-bound are computed from the text itself, while Achievable and
Relevant are explicitly flagged as needing your own judgment about capacity and strategic fit — this connector
doesn't pretend to know your team's workload. okr_examples gives a full original example Objective and three Key
Results per goal area. cascade_guidance explains how OKRs should (and shouldn't) flow from company to team to
individual level. okr_glossary defines OKR terms. scoring_scale_explainer covers the common 0.0-1.0 scoring
convention and the difference between stretch and committed goals. review_cadence_plan computes checkpoint weeks
— kickoff, weekly check-ins, mid-cycle review, final review — across an OKR cycle, with real calendar dates if you
give a start date.
Quality checks are computed heuristics on the text you give — regex and keyword patterns for numbers, dates, and task-like verbs — not a language model judging strategic fit. They'll flag a Key Result with no number or deadline reliably, but they can't tell you whether a target is actually achievable for your team or genuinely relevant to your Objective. The example OKRs are original compositions written for this connector.
Effective 25 September 2026. Unify Dynamics LLC ("we", "us"), Menlo Park, California.
What Okrframe is. Okrframe is a connector (an MCP server and REST API) that AI assistants and personal agents call on your behalf for OKR (Objectives and Key Results) template generation and computed heuristic quality checks, plus hand-curated cascading, scoring-scale and glossary reference. You interact with your assistant; the assistant sends us only the arguments needed for that one request.
What we receive. The arguments of each tool call — a goal area, a draft objective or key result, a cascade level, or a cycle length — the technical headers needed to serve the request (an IP address or a client identifier supplied by the assistant, and a Pro API key if you have one), and standard server logs.
Everything is computed on our server and nothing is stored. Every tool is a local calculation or a lookup against a bundled, hand-curated reference; no request is forwarded to any third party. Text you submit is processed for that one response and is not logged in request bodies, recorded, or used to train anything.
What we do not receive or store. We do not receive your conversation with the assistant, your name, contacts, or account credentials, and we do not build a profile from your requests: each one is answered independently and nothing carries over between requests. Rate-limit counters (a client identifier and timestamps) are held in memory for at most 24 hours. Hosting-provider access logs, which contain IP addresses and request paths but not request bodies, are retained for up to 30 days for security and abuse prevention.
Sub-processors. None — every tool is computed or looked up locally. Hosting: Vercel (United States regions).
Legal bases and your rights. Our processing is necessary to provide the service you request through your assistant. Because we store no personal data beyond short-lived logs, requests to access, correct or delete personal data are usually satisfied automatically; you can still contact agent@connectorbay.com and we will respond within 30 days. We do not sell or share personal information and do not use your data to train models.
Children. Okrframe is a general-audience service operated by the adult using the assistant.
Changes. We will post changes here with a new effective date.
Effective 25 September 2026. These terms govern use of the Okrframe connector ("the Service") operated by Unify Dynamics LLC ("we", "us").
Email agent@connectorbay.com. We answer within two business days.
https://okrframe.connectorbay.com/mcphttps://okrframe.connectorbay.com/openapi.jsonWhen you report a problem, include the question you asked your agent, roughly when, and which agent you used (for example Claude, ChatGPT or Gemini). Never send us passwords, account numbers or ID numbers. OKR Builder never asks for them.