Twilio Elastic SIP Trunking (BYOK)
Read your Twilio Elastic SIP trunks, their origination URLs, phone numbers, IP access control lists, credential list names and recording settings with your own credentials (read-only)
Grant-proposal structure, a real SMART-goal checker, a logic-model explainer, and why proposals get rejected
Unify Dynamics LLC
Real questions, and the tools your agent calls to answer them.
grant_proposal_structuresmart_goal_frameworksmart_goal_checkerlogic_model_explainercommon_rejection_reasonsgrantwriting_glossaryGrantWriting is a fully local grant-proposal-structure toolkit for nonprofits. grant_proposal_structure returns the standard six-section structure (needs statement, goals/objectives, methodology, evaluation plan, budget narrative, sustainability plan) with purpose and content guidance per section. smart_goal_framework explains SMART (Specific, Measurable, Achievable, Relevant, Time-bound). smart_goal_checker evaluates a caller-supplied goal against all five criteria using real text analysis and returns a pass/fail per criterion. logic_model_explainer covers the inputs-activities-outputs-outcomes-impact chain with a worked after-school-tutoring example. common_rejection_reasons is a hand-curated reference of why proposals get rejected, by section, each with a fix. grantwriting_glossary defines terms like logic model, theory of change, letter of inquiry, matching funds, and indirect costs. Not a guarantee of funder approval and not a substitute for a specific funder's own guidelines.
Sources: Computed locally / hand-curated nonprofit grant-writing reference; fully local, zero upstream calls
The publisher, Unify Dynamics LLC, states that tool inputs are processed in memory and not retained.
6 tools, grouped by job. Every one is read-only or compute-only.
https://grantwriting.connectorbay.com/mcpRead your Twilio Elastic SIP trunks, their origination URLs, phone numbers, IP access control lists, credential list names and recording settings with your own credentials (read-only)
Read your Twilio Programmable SIP domains, IP access control lists, credential list names and how they are mapped to domains with your own credentials (read-only)
Read your Twilio call queues and their waiting members, conferences and their participant states, TwiML applications and recording metadata with your own credentials (read-only)
Read your Twilio Proxy services, number pools, sessions and participant proxy numbers for masked calls and messages with your own credentials (read-only)
Read your Twilio regulatory compliance bundles, bundle evaluations and assigned items, regulations and document types for phone numbers with your own credentials (read-only)
Read the Twilio Marketplace add-ons you have installed and the add-ons and extensions available to install with your own credentials (read-only)
"What sections does a grant proposal need", "is 'improve outcomes' a SMART goal, and if not, how do I fix it", "explain a logic model with a real example", "why do grant proposals actually get rejected" -- the structural side of grant writing, answered locally from a hand-curated nonprofit grant-writing reference and a real heuristic checker, without sending your draft goal or proposal text anywhere outside this one call.
grant_proposal_structure returns the standard six-section nonprofit grant-proposal structure in order --
needs statement, goals and objectives, methodology, evaluation plan, budget narrative, sustainability plan --
with each section's purpose and what to include. smart_goal_framework explains the SMART (Specific,
Measurable, Achievable, Relevant, Time-bound) framework used for objectives. smart_goal_checker evaluates a
goal statement you provide against all five SMART criteria using real text analysis -- an actual number for
Measurable, an actual deadline for Time-bound, a named program metric or population for Specific/Relevant, and
a check for absolute/impossible language for Achievable -- and returns a pass/fail per criterion plus an
overall verdict. logic_model_explainer explains the inputs -> activities -> outputs -> outcomes -> impact
chain with a full worked example (an after-school tutoring program), including the key outputs-vs-outcomes
distinction. common_rejection_reasons is a hand-curated reference of why proposals get rejected, organized by
proposal section, each with a fix. grantwriting_glossary defines terms like logic model, theory of change,
letter of inquiry, matching funds, indirect costs, and restricted funding.
Not a guarantee any funder will approve a proposal, and not a substitute for a specific funder's own guidelines, which always take precedence over general structure advice like this. The SMART-goal checker is a heuristic based on text patterns (numbers, dates, named metrics and populations, absolute-language flags) -- Achievable and Relevant in particular are approximated from text alone and are worth double-checking by hand, not treated as a certified verdict. It never writes proposal content for you -- it's a structure and self-check reference, not a proposal-generation tool.
Built and maintained by Unify Dynamics LLC. Contact: agent@connectorbay.com.
Effective 28 September 2026. Unify Dynamics LLC ("we", "us"), Menlo Park, California.
What GrantWriting is. GrantWriting is a connector (an MCP server and REST API) that AI assistants and personal agents call on your behalf for a fully local grant-proposal-structure reference and a SMART-goal checker. You interact with your assistant; the assistant sends us only the arguments needed for that one tool call.
What we receive. The arguments of each tool call — which may include a goal or objective statement you're asking us to check, a proposal-structure or rejection-reasons category, or a glossary term — 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.
We do not store, log, or retain the goal text or any other content you submit. Every tool analyzes the text you send in memory, for that one request, and returns a result — nothing about the content of a goal statement or proposal draft is written to a database, written to a request log, cached, or used to train anything. Request bodies are not logged.
What we do not receive or store. We do not receive your conversation with the assistant or your name, and we do not build a profile from your queries: each request is answered independently and nothing carries over between requests. Rate-limit counters (a client identifier and timestamps, never the request content) 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 — there is no upstream call at all; every tool either analyzes your submitted text locally or reads from a hand-curated reference bundled with the server. 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, content-free 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. GrantWriting is a general-audience service operated by the adult using the assistant.
Changes. We will post changes here with a new effective date.
Effective 28 September 2026. These terms govern use of the GrantWriting connector ("the Service") operated by Unify Dynamics LLC ("we", "us").
Email agent@connectorbay.com. We answer within two business days.
https://grantwriting.connectorbay.com/mcphttps://grantwriting.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. GrantWriting never asks for them.