Fulcrum MCP. Query field data and manage form records via AI.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Fulcrum MCP Server manages field data collection, tracks form records, and queries massive datasets through AI agents. Connect your preferred AI client to automate mobile inspections, surveys, and inventory management.
Your agent can list forms, fetch schemas, retrieve records, and run powerful SQL queries against your field data—all without manual exports or dashboard navigation.
What your AI agents can do
Check api status
Verifies the current connection status of the Fulcrum API.
Create record
Writes a new data record into the system.
Get form schema
Retrieves the field definitions and structure for a specific data form.
Retrieves a list of every data collection app (form) configured in your Fulcrum environment.
Fetches the detailed schema, including field definitions and validation rules, for a specific form ID.
Retrieves a list of collected field data, allowing you to filter the results by a specific form ID.
Retrieves the full metadata and details for a single, known field record.
Generates and writes a new record directly into the database, keeping your field data current.
Executes complex SQL statements against your datasets to filter, join, and analyze large volumes of data.
Lists organization members and available system roles for managing team access and permissions.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
Fulcrum MCP Server: 10 Tools for Field Data Management
Use these ten tools to list forms, get schemas, query records with SQL, and manage user accounts, all through your AI agent.
019d75a1check api status
Verifies the current connection status of the Fulcrum API.
019d75a1create record
Writes a new data record into the system.
019d75a1get form schema
Retrieves the field definitions and structure for a specific data form.
019d75a1get record details
Fetches the full metadata for a single, existing record.
019d75a1list data forms
Lists all the data collection apps (forms) available in your account.
019d75a1list field records
Lists existing field data records, allowing filtering by form ID.
019d75a1list member roles
Lists the available system roles (e.g., Owner, Manager, Standard).
019d75a1list organization members
List team members
019d75a1list webhooks
List webhook configs
019d75a1query records sql
Query data with SQL
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Fulcrum, then connect any of our 4,700+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,700+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
What you can do with this MCP connector
Your AI agent can manage field data collection and track form records directly through Fulcrum. It gives your agent access to everything—all the apps, the data, and the people who use them—without you having to manually export anything or click through dashboards. You'll connect your AI client, and your agent's tools take over.
Your agent can list every data collection app you've built using list_data_forms, and it can grab the specific field structure for any form using get_form_schema. To see what data's out there, your agent lists existing field records with list_field_records, or it fetches all the metadata for one specific record using get_record_details.
You can also generate and write a whole new data record right into the system with create_record. For deep dives, your agent runs custom SQL queries against your entire dataset using query_records_sql.
It handles team management, too. Your agent can list all team members with list_organization_members and check the available system roles, like Owner or Manager, using list_member_roles. You can check the API's live connection status with check_api_status, and it'll list any configured webhooks using list_webhooks.
How Fulcrum MCP Works
- 1 Subscribe to the server via Vinkius and input your Fulcrum API Token.
- 2 Tell your AI agent what data you need (e.g., 'Show me all site inspections from last month').
- 3 The agent selects and runs the appropriate tool (like
query_records_sql) and delivers the structured data response.
The bottom line is that your AI agent treats your entire field database like a single conversation topic, giving you instant, structured data access.
Who Is Fulcrum MCP For?
This is for Operations Managers, GIS Analysts, and Data Architects who are sick of manual data exports. If you manage field inspections, surveys, or asset inventory, and you need to query data across multiple forms or join disparate datasets, this server lets you do it via natural language, bypassing clunky dashboards and manual SQL writing.
Uses the server to quickly check collected record status or query survey datasets without having to manually export data to Excel for reporting.
Prompts the agent to run complex SQL queries against field data, instantly generating filtered reports that normally require a data engineering pipeline.
Automates auditing by listing form schemas, member lists, and webhooks to manage user access and verify data syncs across the system.
What Changes When You Connect
- Query any data instantly. Don't write complex SQL manually. By calling
query_records_sql, your agent runs powerful, filtered queries against your entire dataset, giving you instant reports without leaving the chat interface. - See the full data structure. Use
get_form_schemato understand exactly what data a form collects. You get field definitions and validation rules, letting you know if a record is missing required information. - Automate data entry. Need to log a finding? Use
create_record. Your agent handles the connection and structure, letting you write a new record directly from a natural language prompt. - Manage your workforce. With
list_organization_membersandlist_member_roles, you can automate user audits and check permissions, knowing who has access to which parts of the system. - Streamline inspections. Instead of navigating multiple dashboards, your agent can list forms (
list_data_forms) and then list field records (list_field_records) to give you a complete, auditable view of all collected data. - Audit data connections. Use
list_webhooksto check if your downstream systems are still receiving real-time data syncs, ensuring your field intelligence doesn't get lost.
Real-World Use Cases
Auditing a Site Inspection
A Field Manager needs to know which assets were inspected last week. They tell their agent: 'Run a query for all records from the 'Asset Inventory' form where the date is last week.' The agent executes query_records_sql, returning a filtered list of assets instantly, solving the need for manual date filtering in the dashboard.
Checking Data Integrity
A Data Analyst suspects a form is collecting the wrong information. They ask the agent to run get_form_schema for the form ID. The agent returns the full schema, showing the field types (Text, Choice, etc.) and required status, allowing the analyst to correct the form structure.
Adding a New Record Manually
A System Admin is out in the field and needs to log a quick observation. They prompt the agent: 'Create a new record for the 'Site Inspection' form with condition 'Poor' and notes about drainage.' The agent uses create_record, writing the record to the database and keeping the field worker productive.
Reviewing User Permissions
A Manager needs to see who is assigned to the 'Owner' role. They ask the agent to run list_member_roles and then use list_organization_members to pull the full team list. The agent compiles the access report, saving hours of manual user management.
The Tradeoffs
Calling multiple APIs sequentially
To get the full details of a record, a user might first call list_field_records to get an ID, then call get_record_details using that ID, and then call get_form_schema to understand the field types. This chain of calls is slow and brittle.
→ Instead of chaining three tools, tell your agent the goal: 'Give me the details and schema for the record in the 'Asset Inventory' form.' The agent orchestrates the calls internally, providing the full context in one go.
Assuming API knowledge
A user trying to query data might write vague prompts like 'Show me the site data.' This forces the agent to guess which form or table to query, leading to errors or incomplete results.
→
Be specific and reference the tool: 'Run a query using query_records_sql on the 'Site Inspection' form, filtered for records where the status is 'Failed' and the date is within the last 30 days.' The more specific you are, the better the result.
Ignoring data governance
Trying to guess the correct field name or join key for a complex query and writing an incorrect query_records_sql statement. This fails and wastes time.
→
First, run get_form_schema to understand the precise field names and data types. Then, use that validated knowledge to construct your query_records_sql statement. Start small.
When It Fits, When It Doesn't
Use this server if your primary job involves managing, inspecting, or reporting on physical field data, surveys, or inventory records. You need to query complex, joined datasets (use query_records_sql) and automate data entry (create_record) from natural conversation. Don't use this if you just need to check a single, static list of users or simple configuration settings—those are better suited for dedicated user management or simple list APIs. If your data flow requires knowing the structure of the input forms before you can run a query, this is your tool. If your data is stored in a completely different system (e.g., Salesforce), you need a different category of data integration tool.
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Fulcrum. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 10 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Manually pulling field data is a nightmare of exports and joins.
Today, if you need to see all assets inspected last quarter, you open the Fulcrum dashboard. You filter by date, then you export the results to CSV. If you need to add a new observation, you have to open the form, fill out the fields, hit save, and then maybe copy that record ID into a separate spreadsheet for tracking. It's a dozen clicks, several exports, and a high chance of missing data.
With the Fulcrum MCP Server, you just ask your agent: 'Give me all records from the 'Asset Inventory' form where the condition was 'Poor' in Q2.' The agent runs the necessary `query_records_sql` and hands you the structured, filtered data right in the chat. The data is ready for the next step, no manual exports required.
Fulcrum MCP Server: Automate Data Entry and Schema Checks
Before the MCP Server, if a field worker wanted to know if they were allowed to use a specific field, they had to check the form's backend settings. If they needed to log an observation, they had to navigate the form, click fields, and manually hit 'submit.'
Now, you can prompt your agent: 'What are the required fields for the 'Site Inspection' form?' The agent runs `get_form_schema` and spits out the answer. You can then tell it: 'Create a record using these fields,' and it handles the entire data validation and saving process for you. The whole workflow stays in the chat.
Common Questions About Fulcrum MCP
How do I use the `query_records_sql` tool with Fulcrum MCP Server? +
You prompt your agent with the full SQL query. The agent passes the query to the tool, which runs it against your database and returns the results. You can filter by date, join multiple tables, and group data all in one prompt.
What is the difference between `list_field_records` and `query_records_sql`? +
list_field_records gives you a basic list of records, often filtered by form ID. query_records_sql runs full, custom SQL queries, giving you far more power to join data across different tables or filter on complex criteria.
Can I use `get_form_schema` to validate data types? +
Yes. The get_form_schema tool provides detailed metadata for every field, including its defined data type (Text, Choice, Date) and whether it requires input, letting you validate your inputs before running a query.
How do I ensure the API connection is working with `check_api_status`? +
You simply ask the agent to run the check_api_status tool. It verifies the live connection to the Fulcrum API and tells you if everything is up and running.
Can I list all forms using `list_data_forms`? +
Yes. The list_data_forms tool fetches a list of every data collection app (form) in your account, so you know what data sources are available to query.
How do I manage user access and roles using the `list_member_roles` and `list_organization_members` tools? +
These tools let you audit who's on the team and what they can do. You first use list_organization_members to get the full list of users. Then, list_member_roles shows the specific roles (Owner, Manager, Standard) assigned to them for access control.
What happens if I try to `create_record` with invalid data or a missing field? +
The system will return an explicit error message detailing the validation failure. You can use the schema data from get_form_schema to fix the required fields before attempting to create the record again.
Is there a way to check the status of webhooks using `list_webhooks`? +
Yes, list_webhooks shows all configured webhooks and their current status. This lets you verify that your downstream systems are set up to receive real-time data syncs from Fulcrum.
How do I get an API Token for Fulcrum? +
Log in to your Fulcrum web app, click the Settings (gear icon), select 'API', and you can generate a new API Token.
Can I run SQL queries on my field data? +
Yes! Use the 'query_records_sql' tool. Provide a standard SQL statement (e.g., SELECT * FROM "form_id") to instantly retrieve filtered datasets.
Is it possible to see the schema of a form? +
Absolutely. The 'get_form_schema' tool retrieves the complete JSON definition of a form, including all its field keys, data types, and validation rules.
Can I programmatically create a new record? +
Yes, you can use the 'create_record' tool. You will need the Form ID, latitude, longitude, and a JSON payload containing the specific form values.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
Pitchly
Turn your firm experience data into competitive deal sheets, credentials, and pitch materials with automated content generation.
Discord
Manage Discord servers, post messages, organize channels, and moderate communities with full bot-level API access.
QA Arbiter
A test fails. Is the assertion wrong or is the code broken? Most agents guess, retry blindly, and deadlock the pipeline. QA Arbiter resolves this in one call — structured fault diagnosis with two boolean pivots that yield a deterministic verdict: TEST_ERROR, ENGINE_DEFECT, or BOTH_WRONG.
You might also like
Mosaic (Resource Planning & Workforce Management)
Manage resource planning via Mosaic — track work plans, audit budget estimates, and monitor team capacity.
Automate visual discovery via Pinterest — manage boards, create pins, and track performance directly with AI.
HrFlow.ai
AI-powered talent acquisition API for parsing, matching, and reasoning.