BG Verification
Metamap MCP connector
The Metamap connector lets Claude, ChatGPT, Cursor and other AI clients start identity verifications, run watchlist, email, phone and government record checks, and pull verification results, all inside each person's own Metamap access with every action logged.
-
How it connects. App credentials. The credential goes into a vault nobody reads back.
-
One address. https://api.elaichi.ai/mcp, the same for every user.
-
Their own access. An agent never gets more than the person it acts for.
46 tools
How to connect
How to connect Metamap to Claude, ChatGPT or Cursor
Two steps, about a minute.
In Elaichi
Connect Metamap once
-
Open Connections, choose Add connection, and pick Metamap.
-
Optionally set Share with to give a team access, then press Connect.
-
Paste your Metamap app credentials. Metamap authenticates the app rather than a person. One person supplies the credentials once, and everyone else works through Share with.
The credential is vaulted. Nobody reads it back, not even the AI.
Add connection
Choose a connector.
In your AI client
Point it at one endpoint
Everyone in the organization uses the same address, and each person only ever reaches what their own account allows.
Connect Metamap to Claude
-
1
Open Customize, then Connectors.
-
2
Press Add.
-
3
Name it, paste the MCP server URL, then Continue.
https://api.elaichi.ai/mcp -
4
Sign in and approve.
On Team and Enterprise, an Owner adds it once. Everyone else turns it on for themselves.
Connect Metamap to ChatGPT
-
1
Open Plugins, then press the + button.
-
2
Name it and paste the endpoint into Server URL.
https://api.elaichi.ai/mcp -
3
Leave Authentication on OAuth, then tick the risk acknowledgement.
-
4
Press Create, then sign in and approve.
Works on the web today. The plugin directory lives at chatgpt.com/plugins.
Connect Metamap to Cursor
-
1
Open
~/.cursor/mcp.json. -
2
Add the endpoint under
mcpServers.https://api.elaichi.ai/mcp -
3
Reload Cursor, then sign in and approve.
~/.cursor/mcp.json
{
"mcpServers": {
"elaichi": {
"url": "https://api.elaichi.ai/mcp"
}
}
}
Set up per machine, so repeat it on each computer you work from.
Connect Metamap to any MCP client
-
1
Add the endpoint as a remote MCP server.
https://api.elaichi.ai/mcp -
2
Sign in and approve.
{
"mcpServers": {
"elaichi": {
"url": "https://api.elaichi.ai/mcp"
}
}
}
The Elaichi Agent already has these tools, with nothing to set up.
Use cases
What teams do with Metamap through Elaichi
Every one of these runs inside the access the person already has, and lands in the same audit log.
-
Compliance
Screen a new customer against watchlists
Ask for a sanctions and adverse media screen on an applicant, or check them against your own custom watchlist, and get the result back in plain language before anyone approves the account.
-
Onboarding
Start a verification while the applicant waits
Kick off a new Metamap verification from a chat, add the applicant's details, and check its status a few minutes later without opening another tab.
-
Risk
Check an email or phone before approving
Ask whether the email address and phone number on an application belong to the person and how risky they look, then decide whether to move forward.
-
Compliance
Validate a Brazilian CPF or CNPJ
Run a CPF validation for an individual or an extended CNPJ lookup for a company in Brazil and get the government record findings summarized in one place.
-
Operations
Pull the verification report for a file
Ask for the PDF download of a completed Metamap verification, along with a list of its uploaded media, when an auditor or partner requests the evidence.
-
Support
Clear a stuck verification queue
Skip a verification an applicant has abandoned, update a batch of verifications at once, or look up a single one by ID when a customer asks why their check has not finished.
Try asking
- “Show verifications created this week by team.”
- “List watchlist hits still awaiting review.”
- “Summarize failed email and phone risk checks.”
AI tools
Metamap tools for your AI agents
46 tools are ready to call through Elaichi's MCP endpoint the moment you connect Metamap, governed by the same roles, restrictions, and audit log as everything else in Elaichi.
No tools match your search.
See it in Elaichi
What connecting Metamap gets you
6 screens from the product, each doing one job for your Metamap account.
The agent
Ask about verifications, get answers back.
Plain language questions run against live Metamap verifications, watchlist hits and media.
- verifications
- watchlist hits
- risk checks
- media
Ask Elaichi to work across your apps.
Show verifications created this week by team.
List watchlist hits still awaiting review.
Summarize failed email and phone risk checks.
Also runs in Claude, ChatGPT or Cursor
MCP clients
Claude, ChatGPT and Cursor reach Metamap.
One governed OAuth endpoint for every MCP client, no SDK, no shared API key.
ElaichiMCP clientsClaude
ChatGPT
Cursor
Copy the endpoint
Tool catalog
46 Metamap tools, zero custom code.
Verifications, inputs, media, watchlists and risk checks are cataloged and ready to call.
- Create a Metamap verification
- Get single Metamap verification by ID
- Delete a Metamap verification by ID
- Metamap verifications skip
ElaichiToolsToolboxes
Every team gets its own toolbox.
Compliance, onboarding and risk each see a Metamap toolbox scoped to their work.
- Compliance
- Onboarding
- Risk
- Fraud
ElaichiToolboxesShared connections
Teammates run checks without seeing credentials.
One Metamap connection, shared to named teams and members, owner recorded on every row.
- Compliance EMEA
- Onboarding
- Risk Review
- Fraud Desk
ElaichiConnectionsAudit log
Every verification call is written down.
When, who, what happened, type and resource, appended for each Metamap request.
- When
- Who
- What happened
- Type
ElaichiAudit logLaunching soon
From answering questions to doing the work
A person no longer has to ask. A trigger starts the work, inside the same permissions and the same audit log as everything else. Automations and live dashboards are launching soon, on the Black plan.
Automations
A schedule starts the review, not you.
Fetch Metamap verifications, group them, draft a digest, approve, post the result back.
Metamap digest
Run 418 · started 2 minutes ago · on behalf of Emma Laurent
-
✓
Schedule
Every weekday at 08:00
0.2s -
✓
Fetch verifications
Metamap
1.4s -
✓
Group by owner
Transform
0.1s -
✓
Draft the digest
Agent step
Ran with 4 tools, returned a structured summary
6.2s -
Approve the digest
Needs approval
Assigned to Michael Brennan
Approve Deny -
Post the digest
Metamap
Queued
Collections and dashboards
Verification health arrives before anyone asks.
Four metrics, 14 days of new verifications and a team breakdown, refreshed on schedule.
Metamap health
Refreshed 4 minutes ago · every 15 minutes · from the verifications collection
Verifications
1,284 ↓ 12%
Watchlist hits
96 ↓ 8%
Needs attention
3 ↑ 2
Updated this week
412 ↑ 9%
Verifications created
Last 14 days
By team
Share of activity
Compliance EMEA 34%
Onboarding 27%
Risk Review 21%
Fraud Desk 18%
Related connectors
More from the catalog
FAQ
Frequently asked questions
How do I connect Metamap to Claude?
First connect Metamap inside Elaichi by entering the app credentials from your Metamap account, and Elaichi confirms the connection on the spot. Then open Claude, go to Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp as the endpoint. There is no OAuth application to register and no client ID or secret to generate, and the whole process takes a few minutes.
Does Metamap work with ChatGPT and Cursor as well as Claude?
Yes. Once Metamap is connected in Elaichi, the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, any other MCP client and the Elaichi Agent. You connect Metamap once and every client your team uses can reach it.
What can an AI agent actually do with my Metamap data?
With Metamap connected, an agent can start a verification for an applicant, add their details, check on its status, list its uploaded media and pull the PDF report. It can also run screening on your behalf: sanctions and watchlist checks, email and phone ownership and risk checks, and government record lookups in Brazil, Chile, Colombia and Costa Rica. Because Metamap offers many actions, short concrete asks such as "run a phone risk check on this number" work better than long paragraphs.
Does connecting Metamap give the AI access to every verification in my account?
No. Every request to Metamap runs as the person who signed in, so the agent can only see and do what that person can already see and do in Metamap. Elaichi can narrow that access further, for example to read-only or to specific checks, but it can never widen it beyond what Metamap itself allows that person.
Can I stop an agent from deleting or changing verifications in Metamap?
Yes. Restrictions in Elaichi work per action, so you can block deleting a Metamap verification, skipping one or updating a batch while still allowing checks and lookups. A blocked action is never shown to the AI client at all, so no prompt, however it is worded, can reach it.
What happens to a Metamap connection when someone leaves?
Offboarding a person in Elaichi ends their access to Metamap through every client at once, whether they connected it themselves or used a shared connection. A shared Metamap connection keeps working for everyone else on the team. If you want to remove Metamap entirely, disconnecting it once in Elaichi removes it from Claude, ChatGPT, Cursor and every other client at the same time.
Put Metamap in front of your team
Fourteen days on Gold, no credit card. Connect it once and pick what each team can call.