Lattice MCP. Access employee profiles and performance metrics from Lattice HR.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Lattice MCP Server lets your AI agent access detailed employee data, OKRs, and performance records from Lattice HR. You can list all users, pull full employee profiles, check active goals, and retrieve continuous feedback and formal reviews.
Stop switching between HR dashboards and your IDE; pull structured people data directly into your workflow.
What your AI agents can do
Get feedback
Gets the full details for a single feedback entry in Lattice.
Get goal
Retrieves specific details about one targeted OKR or goal.
Get review
Gets the details for a specific performance review cycle.
Fetch specific user metadata, including roles and department details, using get_user.
List all active goals and retrieve specific details for a targeted OKR using list_goals and get_goal.
List all instances of praise and continuous feedback, or pull the full content of a single feedback entry using list_feedback and get_feedback.
List all past and current performance review cycles, and get specific data for any given review using list_reviews and get_review.
Get a list of pending tasks assigned across the organization using list_tasks.
Pull a complete list of all employees from Lattice using list_users.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
019d75c4get feedback
Gets the full details for a single feedback entry in Lattice.
019d75c4get goal
Retrieves specific details about one targeted OKR or goal.
019d75c4get review
Gets the details for a specific performance review cycle.
019d75c4get user
Retrieves all profile data for a single Lattice employee.
019d75c4list feedback
Retrieves a complete list of all recorded feedback and praise instances.
019d75c4list goals
Gets a full list of all active OKRs and organizational goals.
019d75c4list reviews
Retrieves a list of all past and current performance review cycles.
019d75c4list tasks
Gets a list of all pending tasks across the organization.
019d75c4list users
Retrieves a full roster and basic metadata for every employee in Lattice.
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 Lattice, 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
Lattice MCP Server lets your AI agent grab detailed employee info, OKRs, and performance records straight from Lattice HR. You don't gotta jump between the HR dashboard and your IDE anymore; your agent pulls structured people data right into your workflow. You can use list_users to grab a full roster and basic metadata for every employee.
You can then use get_user to pull all the profile details for any single employee. You'll manage OKRs and goals by using list_goals to get a full list of active organizational goals, and then use get_goal to pull specific details on a targeted OKR. Your agent checks performance history by calling list_reviews to retrieve a list of all past and current performance review cycles, and then it uses get_review to get the specifics for any given review.
You can audit feedback by using list_feedback to get a complete list of every recorded piece of feedback and praise, or you can use get_feedback to pull the full content for a single feedback entry. You can also check what's pending by getting a list of all tasks across the organization with list_tasks.
How Lattice MCP Works
- 1 First, subscribe to the endpoint and securely enter your Lattice API token.
- 2 Next, your AI client uses the agent to call a specific tool, like
list_users, passing required parameters. - 3 The server executes the query against Lattice and returns structured JSON data to your client.
The bottom line is, your agent runs HR queries against Lattice without you ever leaving your development environment.
Who Is Lattice MCP For?
This is for HR Business Partners who need to pull performance data fast. It's for Team Leads who shouldn't context switch to check team OKRs. And it’s for Engineering Managers who need to read feedback forms right in the IDE—all without logging into a separate HR dashboard.
Pulls bulk performance data for reporting, gathering user lists (list_users) and checking performance records (list_reviews) quickly.
Checks the progress of team OKRs (list_goals) and monitors team engagement by listing recent praise (list_feedback) without leaving Slack or their terminal.
Reads continuous feedback forms (get_feedback) and pulls user directory data (get_user) directly into the IDE to inform project planning.
What Changes When You Connect
- See the full team roster instantly using
list_users. You get all basic employee metadata without running a separate report in the HRIS. - Track team progress by calling
list_goals. You immediately see which OKRs are active and what percentage of the target has been hit. - Audit continuous praise by running
list_feedback. You pull a list of recent mentions and recognize who's getting kudos across the company. - Get a deep dive into employee history using
get_review. You pull the structured data for any past performance review cycle right into your script. - Pull user-specific data with
get_user. You get the full profile of an individual employee, not just their name, for deep analysis. - Review pending action items by using
list_tasks. You get a clear, structured list of all tasks assigned that need attention.
Real-World Use Cases
Need to audit Q2 performance metrics?
Instead of navigating to the review portal, you ask your agent to run list_reviews. The agent finds all relevant cycles, and then you use get_review to pull the specific data for the managers you need to check up on.
Who worked on the latest feature and what did they achieve?
You ask your agent to find all related users. It runs list_users to get the directory, then uses get_user to pull profiles. Finally, it calls list_feedback to see who received praise for the effort.
What is our team's current focus and who is responsible for the tasks?
Your agent first calls list_goals to understand the high-level OKRs. It then calls list_tasks to map out the immediate, actionable items tied to those goals.
I need a list of everyone and their current goals.
You run list_users to get the employee roster. Then, for each user, the agent calls get_user and get_goal to pull and cross-reference their specific profile data with their current goals.
The Tradeoffs
Treating Lattice as a simple database query
Trying to run a complex SQL query like SELECT * FROM users WHERE department='Marketing' AND goals='Q2' in a generic API call.
→
Don't try to write complex SQL. Instead, use the dedicated tools. Run list_users to filter the roster, then use get_user and list_goals to pull structured, specific data based on Lattice's model.
Manually compiling feedback reports
Exporting dozens of feedback entries from the web UI, pasting them into a spreadsheet, and trying to find patterns.
→
Use list_feedback to pull all raw feedback data into your script. Then, use your AI client to process that structured data and summarize trends, saving hours of manual work.
Forgetting the difference between list and get
Calling get_user without an ID, causing the tool to fail because it needs a specific user identifier.
→
Remember: list_users gives you the list, and get_user requires a specific ID from that list to pull the details for one person.
When It Fits, When It Doesn't
Use this server if your workflow requires structured human resource data—like OKRs, feedback, or performance reviews—to make a decision or generate a report. For instance, if you need to determine team readiness, you'll run list_goals and cross-reference it with list_tasks. Don't use it if you just need to read a public-facing company announcement or if you only need a list of names and emails (a simple directory tool is better). If you only need to calculate a simple metric (e.g., average salary), you're better off using a dedicated payroll API instead. This server is for structured, performance-related data.
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Lattice. 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 9 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Checking employee status shouldn't take three different dashboards.
Today, checking an employee's status means logging into the HRIS, checking their OKRs in a separate dashboard, and then digging into their performance reviews in a third tool. You copy names, you jump tabs, and you spend fifteen minutes just trying to assemble a coherent picture.
With this MCP server, your agent pulls everything into one structured output. You ask for a user's profile, their active goals, and their last review score, and it delivers the combined JSON package in seconds.
Lattice MCP Server: Pulling Performance Data
You no longer have to manually search for who gave praise or compile a list of tasks across departments. The agent runs `list_feedback` to get all recent recognition and `list_tasks` to see immediate action items.
The data is structured and actionable. You don't just get a list; you get the data needed to build a report, an update, or a system trigger. That's the difference.
Common Questions About Lattice MCP
How do I use the `get_user` tool in the Lattice MCP Server? +
You must provide the unique ID of the employee. The tool pulls the full profile data for that specific user, including metadata like department and manager.
What is the difference between `list_goals` and `get_goal` in the Lattice MCP Server? +
list_goals pulls a list of all active OKRs and goals across the organization. get_goal requires a specific ID and pulls the detailed status and targets for just one goal.
Can I list all performance reviews using `list_reviews`? +
Yes, list_reviews fetches a list of all available review cycles. You then use get_review with a specific cycle ID to get the actual performance data.
What kind of data does `list_feedback` return? +
It returns a list of all continuous feedback entries and praise instances. Each entry includes who gave the feedback, who received it, and the specific text.
How do I handle rate limits when using `list_users` in the Lattice MCP Server? +
The server returns a standard HTTP 429 error when rate limits are hit. Implement a backoff strategy that waits exponentially longer between retries. You can check the Retry-After header for the exact wait time.
What parameters are required to successfully call `get_feedback`? +
You must provide a unique feedback ID. This ID is necessary to pinpoint the exact feedback entry you want details on. The tool expects the ID as a string.
If I need to find a specific task, should I use `list_tasks` or `get_user`? +
list_tasks retrieves a list of pending tasks directly. Use this tool when you need a general overview of all tasks. Use get_user only if the task is tied specifically to a user's profile.
Can I get a list of all performance review cycles using `list_reviews`? +
Yes, list_reviews fetches a comprehensive list of all performance review cycles. This list includes the cycle name, dates, and the reviewer's name, allowing you to select the specific cycle ID.
How do I authenticate? +
You need a Lattice API Key configured via Admin settings, passed into the plugin's configuration.
Can I update OKRs from this server? +
Currently the server is heavily optimized for reading OKRs, directories, and feedback.
Is employee personal data secure? +
Yes, queries route directly from your Vurb client strictly and securely into the Lattice native endpoints. Nothing is stored intermediately.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
Zoho Desk
AI-powered helpdesk: manage tickets, contacts, and support workflows via agents.
Uselessfacts
Access a vast database of quirky, useless facts to entertain, break the ice, or learn something new every day.
Miro (Visual Collaboration & Whiteboarding)
Manage collaborative boards via Miro — create sticky notes, list visual items, and audit team members.
You might also like
Collibra
Enable your AI agent to manage data assets, domains, and communities via the Collibra Data Intelligence API.
Neon
Manage serverless PostgreSQL databases via Neon — provision projects, branches, endpoints and roles from any AI agent.
Abridge (AI Clinical Documentation API)
Automate clinical documentation with Abridge — create recordings, track processing status, and retrieve structured medical notes directly via AI.