Formio Uag
Form.io's UAG brings their JSON schema forms into the MCP world, giving AI agents the same structured understanding of forms that their JavaScript renderer gives humans. You get two main tools: one converts natural language into validated form submissions, the other lets agents analyze existing submission data and contribute their own fields based on configurable criteria. Think automating college application reviews where an agent reads a student's essay and academics, then fills out an evaluation form following your rubric. The criteria lives in special content components with a uag property, agent fields get tagged with matching personas, and the whole thing works with their open source platform. Best for workflows where you need AI to both understand and contribute to structured data collection processes.
- GitHub stars
- 12
- tools
- 10
- auth
- Secret needed
- transport
- HTTP
- env vars
- 15
- last updated
- Aug 5, 2026
Tools
10 toolsPublic tool metadata for what this MCP can expose to an agent.
get_formsProvides the AI agent with a list of available forms. It will only return forms that have been tagged `uag`.
Provides the AI agent with a list of available forms. It will only return forms that have been tagged `uag`.
No parameter schema in public metadata yet.
get_form_fieldsWhen the AI agent infers the user intends to use a specific form, this tool provides the agent with a high level overview of all the fields needed (along with the field data path) to submit that form.
When the AI agent infers the user intends to use a specific form, this tool provides the agent with a high level overview of all the fields needed (along with the field data path) to submit that form.
No parameter schema in public metadata yet.
get_field_infoOnce the fields have been determined using `get_form_fields`, this tool provides specific information about the requested fields, such as validation, conditionals, input formats, etc.
Once the fields have been determined using `get_form_fields`, this tool provides specific information about the requested fields, such as validation, conditionals, input formats, etc.
No parameter schema in public metadata yet.
collect_field_dataProvides the AI agent with a mechanism to dynamically collect the required information from the user, parsing the user's input into multiple fields at once.
Provides the AI agent with a mechanism to dynamically collect the required information from the user, parsing the user's input into multiple fields at once.
No parameter schema in public metadata yet.
confirm_form_submissionThis tool is used to provide a summary of all data collected before a submission is made to the form.
This tool is used to provide a summary of all data collected before a submission is made to the form.
No parameter schema in public metadata yet.
submit_completed_formProvides the AI agent with the ability to submit all of the data collected from the user to create the form submission.
Provides the AI agent with the ability to submit all of the data collected from the user to create the form submission.
No parameter schema in public metadata yet.
find_submissionsEnables the agent to parse a user's natural language request into a query for a submission, or a specific field of a particular submission.
Enables the agent to parse a user's natural language request into a query for a submission, or a specific field of a particular submission.
No parameter schema in public metadata yet.
submission_updateProvides the AI agent with the ability to update an existing submission, either by supplying unfilled fields or updating existing ones if allowed.
Provides the AI agent with the ability to update an existing submission, either by supplying unfilled fields or updating existing ones if allowed.
No parameter schema in public metadata yet.
agent_provide_dataEnables an AI Agent to analyze existing submission data according to rules defined with a configurable Criteria, and to provide generated data for fields configured for a specific persona.
Enables an AI Agent to analyze existing submission data according to rules defined with a configurable Criteria, and to provide generated data for fields configured for a specific persona.
No parameter schema in public metadata yet.
fetch_external_dataThis tool enables an AI Agent to pull external data into a form workflow through the use of either a Resource component, Select with URL, or a Data Source component.
This tool enables an AI Agent to pull external data into a form workflow through the use of either a Resource component, Select with URL, or a Data Source component.
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageConfiguration
PROJECT*API endpoint to Enterprise project or OSS server
PROJECT_KEYsecretProject API Key (Enterprise) or ADMIN_KEY (OSS)
ADMIN_KEYsecretServer admin key for Community Edition. Not required for Enterprise deployment.
UAG_LICENSEsecretLicense for Enterprise deployment. Not required for Community Edition.
JWT_SECRET*secretSecret used to generate and validate JWT tokens
PORTServer port (default: 3200)
PROJECT_TTLProject cache refresh interval in seconds (default: 900)
JWT_EXPIRE_TIMEJWT token expiration in seconds (default: 3600)
PORTAL_SECRETsecretEnterprise Portal connection secret
MONGOsecretDirect MongoDB connection URI (Enterprise)
MONGO_CONFIGMongoDB driver configuration (JSON)
BASE_URL*The URL clients reach the UAG at. Published in the .well-known OIDC (PKCE) definitions and used for authentication callbacks, so remote agents cannot authenticate without it. Must be a public URL when remote agents connect in; a private or localhost URL is fine for a local MCP cl
LOGIN_FORMPublic URL to login form JSON endpoint
CORSCORS domain or JSON configuration (default: *)
DEBUGDebug logging filter (e.g. formio.*)
Readme
The Form.io Universal Agent Gateway (UAG)
Developer docs · Agentic Coding Plugin · Quickstart · All documentation
Details
- Repository
- github.com/formio/uag
- Website
- form.io
- Categories
- AI & LLM Tools, Automation & Workflows
- Package
@formio/uag- Transport
- HTTP
- Auth
- Required
- Registry
- MCP registry, active
Related AI & LLM Tools MCP servers
View all
DataDoe MCPdeltologic/datadoe-mcpHosted Amazon Seller and Vendor MCP server for Claude, ChatGPT, Cursor, Codex, Gemini, Copilot.9stars
Dakera Mcpdakera-ai/dakera-mcpAgent memory engine — 106 MCP tools, self-hosted, single Rust binary9stars
Lorejordanhindo/loreLightweight MCP for infinite agent memory. Any agent, any session, anytime.9stars
Token Compressorbase76-research-lab/token-compressorCompress prompts 40-60% using local LLM + embedding validation. Preserves all conditionals.8stars
MINDtheastraway/mind-mcp-serverMIND knowledge-graph memory for agents. 44 tools: CRM, Life, MoneyMIND, Budget, Sheets, Email, Sign.7stars