Sansan MCP. Find deep contact details from your entire network.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Sansan connects your AI agent directly to your secure, digitized network of business cards and contacts. It lets you list all scanned cards, search by name, and build deep profiles for people across different departments or projects.
You stop manually digging through spreadsheets; you ask your agent to find the contact details instantly.
What your AI agents can do
Get biz card
Gets all specific data points for a single business card ID.
Get person
Pulls the full, unified profile details for a known contact person ID.
List biz cards
Generates an exhaustive list of every business card recorded in your system.
Use an ID to pull a complete person record, combining all known details from multiple business cards.
Shows a list of every single business card you've ever scanned or entered into the system.
Filters your entire network to find cards that match a specific name, giving multiple matches if necessary.
Lists all departments and registered users, allowing you to audit the organization's current setup.
Retrieves a list of all classification tags used across your cards, helping you understand how the data is organized.
Ask AI about this MCP
Supported MCP Clients
OAuth 2.0 Compatible Gemini Waiting for input…
Sansan MCP Server: 8 Tools for Contact & Card Management
Use these tools with your AI client to list all cards, search contacts by name, and build unified profiles from your entire digitized professional network.
Make your AI actually useful.
Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.
Start using Sansan on Vinkius019d7603get biz card
Gets all specific data points for a single business card ID.
019d7603get person
Pulls the full, unified profile details for a known contact person ID.
019d7603list biz cards
Generates an exhaustive list of every business card recorded in your system.
019d7603list departments
Shows a complete listing of all department names registered within the organization.
019d7603list persons
Lists every unique contact person found across all scanned business cards.
019d7603list tags
Retrieves a list of every classification tag used to organize the data.
019d7603list users
Shows all individual Sansan user accounts registered in the organization.
019d7603search biz cards
Searches your card database using a name or keyword to find matching business cards.
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 Sansan, then connect any of our 4,900+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,900+ 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
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Sansan. 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 8 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Finding contact details shouldn't require jumping between five different tabs.
Today, if you need to know who works at Acme Corp and what their title is, you might start in your CRM (to find the client record), then open a separate networking tool (to see associated cards), and finally check an HR system or internal wiki just to confirm their current department. It’s clicking, copy-pasting, and cross-referencing.
With this MCP server, you tell your agent: 'Find me the details for Jane Doe at Acme.' The agent runs `search_biz_cards` first, confirms her identity, then uses `get_person(id)` to pull together the full record—title, department (via `list_departments`), and phone number—all in one go.
Sansan MCP Server: Get a unified view of your entire contact network.
Before this, if you found five cards for the same person over different years, you had to manually reconcile them. You'd have one card with their old title and another with their new email, forcing you to keep three separate records in your head.
Now, running a single query allows the AI client to merge those disparate records. It uses `get_person(id)` to create one unified profile that shows all historical data points—it's clean, it's comprehensive, and it’s ready to use.
What you can do with this MCP connector
Look, this isn't some generic data dump. Sansan connects your AI agent straight into your secure network of business cards and contact records. It turns a pile of scanned cards—data that used to live in dusty spreadsheets or random folders—into an organized, searchable graph. When you use it, your agent doesn't just read data; it acts on it.
You stop digging through files yourself.
If you need to know what cards are floating around, start with list_biz_cards. That tool gives you an exhaustive rundown of every single business card ever scanned or logged in the system. Need something specific? Use search_biz_cards and feed it a name or keyword. It filters your entire network instantly and spits back matching business cards, even if there are multiple hits.
Once you've found a potential match or an ID, you can drill down deep. To get every tiny detail off one specific card, run get_biz_card using its unique identifier. For a holistic view—combining all known details from multiple cards and sources—you use get_person. This pulls the full, unified profile for any contact person ID you give it.
It’s how your agent builds out complete profiles.
Understanding who works where is half the battle. If you want to map out the company structure, your agent can run list_departments to show every department registered in the organization. You also need to know the people running things; list_users shows all individual Sansan accounts. To see every unique person that's been logged across all those cards, use list_persons.
This gives you a master list of contacts.
It’s not just names and departments either. The system uses tags to organize the chaos, and you can pull that whole context using list_tags—it shows every classification tag used across your data set, helping you figure out how things are grouped. You don't have to manually check all these tools; your agent handles it.
Give it a prompt like, 'Find me the full profile for John Smith in Marketing and show me every department he reports into,' and it pulls everything together using those connections.
Basically, you connect your AI client, and suddenly that messy pile of networking data is structured. Your agent doesn't just read; it connects dots between cards, people, departments, and tags so you get actionable information straight away.
019d7603-31b8-70f6-9151-78b6359c209d 
How Sansan MCP Works
- 1 1. Subscribe to this server and enter your Sansan API Key into your MCP client.
- 2 2. Prompt your agent with a high-level request (e.g., 'Find the CEO of Acme Corp').
- 3 3. The agent executes multiple tools (
list_users,search_biz_cards, etc.) to gather data and returns the structured contact information.
The bottom line is that your AI client acts as a universal connector, running the necessary API calls in sequence so you don't have to.
Who Is Sansan MCP For?
Anyone who deals with high volumes of networking data and needs instant access to contact details. Think sales reps who need client info before a meeting or operations managers auditing company structure. If your job involves going from paper card pile to structured database, this is for you.
Needs to instantly pull the correct title and department of a prospect by name before joining a sales call.
Uses list_persons to see every person associated with an account across multiple historical cards, ensuring no contact is missed.
Runs list_departments and checks user accounts (list_users) to audit the company's official organizational structure.
What Changes When You Connect
- Stop clicking through multiple tabs to find one person. Using
search_biz_cardsand thenget_person(id)lets your agent pull together a single, unified profile instantly. - Audit organizational structure without logging into HR software. Running
list_departments()andlist_users()quickly maps out who belongs where in the company. - Never lose a networking lead again. You can use
list_biz_cardsto see every scanned card, then runget_biz_card(id)on any specific one for details. - Get context on contacts' roles and projects. The
list_tags()tool lets you know exactly how the data was categorized when it came in. - Keep your CRM workflow intact. Your agent pulls necessary contact info without forcing you to leave your primary application, making calls faster.
Real-World Use Cases
The Post-Conference Debrief
A sales rep attended a conference and collected 50 cards. Instead of manually entering them into the CRM, they ask their agent to 'Process all new contacts.' The agent uses list_biz_cards first, then runs get_person(id) on each one, grouping redundant data points into clean records.
Auditing Internal Structure
An ops analyst needs to check if a project team has the right people. They run list_departments() and then cross-reference that list with list_users() to verify every required role is accounted for.
Finding an Old Connection
An executive needs contact details for a former colleague, but only remembers the name 'Garcia'. They use search_biz_cards and narrow down the results. Then they run get_person(id) to get the full current phone number.
Data Cleanup Before Migration
Before moving data, a user runs list_tags() and checks for duplicates using list_persons(). This ensures all unique contacts are captured before they lose access to the source system.
The Tradeoffs
Searching without context
Trying to guess an ID or asking the agent for 'all department contacts' without knowing which specific card/user you mean.
→
Always start by narrowing the scope. Use search_biz_cards first with a name, then if needed, use that result to find the correct person ID and pass it to get_person(id) for accurate data.
Ignoring card lists
Assuming that simply asking for 'all contacts' will give you a clean list, when in fact the agent needs explicit permission or steps to run through every record.
→
Always start with list_biz_cards() if your goal is maximum coverage. This gives the AI client the full scope of available data before it attempts extraction.
Mixing up roles
Asking for a 'user profile' when you actually need contact details from a scanned card, which will fail to find the right records.
→
If the source is a physical card, use get_biz_card(id). If the source is an established system account, use get_person(id).
When It Fits, When It Doesn't
Use this server if your primary challenge is converting unstructured or scattered contact data (like scanned cards and old networking notes) into a single, searchable record. It's critical for directory lookups where the source material is messy, but the output needs to be clean.
Don't use it if you just need to validate an email address against a public database; other dedicated verification services are faster. Also, don't rely on this server if your relationship data requires custom join logic across multiple external systems—it provides structured access to Sansan, but isn't the master relational graph itself.
The best pattern is: Start with list_persons() to see who exists. Use search_biz_cards for initial discovery. Only use targeted tools (get_person, get_biz_card) once you have a confirmed ID.
Common Questions About Sansan MCP
How do I find a person who was at a conference last year using `search_biz_cards`? +
You search by name first. If that gets too many results, you'll need to use the system tags. Run list_tags() to see available event tags, then ask your agent to filter contacts attached to that tag.
Does `get_person(id)` combine data from all my business cards? +
Yes. The function is designed to merge records. It pulls together the best available details (title, phone, email) across multiple physical or scanned cards associated with that single person ID.
What if I only know a department name? Can I find users using `list_departments()`? +
You can list the departments first. Then you use those results to filter your search for users by asking the agent to look up contacts within that specific departmental group.
Which tool should I use if I just want a raw dump of every card? +
You must use list_biz_cards(). This tool doesn't analyze or filter; it simply returns the complete, unedited list of every ID in your database for you to work with.
What happens if I try to use `get_biz_card(id)` with an invalid card ID? +
The API returns a specific error code and message. Your AI client handles this gracefully by notifying you that the provided identifier does not match any existing records in your Sansan database.
If I run many requests using `list_persons` quickly, is there a rate limit? +
Yes, usage is governed by API rate limits. If you hit the cap, the connection will pause and automatically retry the request after a short delay. We recommend building retries into your agent's workflow for large data pulls.
How secure is the data accessed when I call `list_users()`? +
Access to user lists strictly adheres to the permissions tied to your API key. Your AI client only sees the organizational structure and users you are authorized to view, ensuring data segregation.
Do I need to know how tags were created when using `list_tags()`? +
No, you just need to know which tags exist. The list returned by list_tags() provides the exact naming conventions and categories that your AI agent can use later for filtering contacts.
Can my AI agent find a specific business card by just a first name? +
Yes. Ask the agent to run the search_biz_cards tool with the contact's name. It will look through all digitized cards in the shared corporate database and return the matching profiles, including their company, department, and direct contact details.
Is it possible to list only contacts from a specific department? +
Yes, you can ask your agent to first execute list_departments to view your organizational structure, and then cross-reference those entities with the cards via natural prompts to summarize card acquisitions per department.
What is the difference between business cards and persons? +
Business Cards are individual scan snapshots of physical cards acquired over time. A 'Person' represents the consolidated identity created when multiple updated cards from the same individual are merged. You can query both views via list_biz_cards or list_persons.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.