MCP agent integrations

Give your AI tools the relationship
context they are missing.

Bridge's MCP server lets Claude, Cursor, or your own agent search contacts, log activity, set reminders, and make scoped updates — with an audit trail and safety rails.

Capabilities

What connected agents can do.

You choose the capabilities each token can see. Reads are the safe default; writes require an explicit scope.

Pending transfer

Send a pending contact transfer

A scoped agent can create a pending transfer to another Bridge user. The recipient or their explicitly scoped agent can accept or decline it.

bridge_contacts_transfer

Search your contacts

Search by name, company, school, location, role, or relationship keywords. Bridge returns the contacts that match the question.

bridge_contacts_search

Log calls and notes

Tell the agent what happened and it can write a scoped activity entry attached to the right contact.

bridge_activity_log

Create reminders

Tell the agent to nudge you about the founder you met at dinner in three weeks. It schedules, you forget, Bridge remembers.

bridge_reminders_create

Update contact details

New email, new fund, new title — the agent can update an allowed field and Bridge records what changed.

bridge_contacts_update

Move deals between stages

Deal-stage changes require confirmation before Bridge applies them. The invocation stays in the MCP audit record.

bridge_deals_move_stage
How it works

Three steps. No SDK.

Bridge speaks MCP and HTTP directly. If your agent can read JSON, it can work with Bridge.

01

Mint a token

Open your Bridge settings and create an MCP token. Pick exactly which capabilities the agent gets: read-only, write, or specific actions like reminders.

02

Point your agent at Bridge

Add the Bridge MCP endpoint to Claude Desktop, Cursor, or another MCP host. No SDK or custom integration layer required.

03

Review the work

The agent discovers only the tools in its scope. Bridge records each invocation, and higher-impact actions keep their confirmation or review step.

Built for trust

Your agent only gets the scope you grant it.

Bridge keeps access narrow, sensitive data optional, and higher-impact actions reviewable.

PII stays out of the prompt

Tokens scoped to non-PII access get emails, phone numbers, and notes stripped before the agent ever sees them. The agent works with handles, not addresses.

Undo where it is safe

Supported reversible writes return a one-shot undo token. Bridge also reports side effects that an undo cannot pull back.

Higher-impact moves ask first

Deal-stage changes use a confirmation step before Bridge applies them. You can approve or cancel from the agent conversation.

Tokens never widen silently

Each token carries an allowlist. Wildcards stay scoped to what you picked. A read token can never quietly grow into a write token while you sleep.

Roadmap

What is available, and what remains controlled.

Manual tokens support a broader scoped toolset today. OAuth writes remain a controlled rollout.

Available now
  • Scoped contact and relationship-activity search
  • Explicitly allowed activity, reminder, contact, and deal writes
  • Pending contact transfers between Bridge users
Controlled rollout
  • OAuth write access for approved beta accounts
  • Confirmation before deal-stage changes
  • Audit records for MCP invocations
Exploring
  • Cross-firm introduction requests with explicit consent
  • Agent-assisted meeting preparation
  • Shared trust signals without exposing private context

Connect your agent without
handing over the whole network.

You choose the scope. Bridge provides the relationship context, audit trail, and safety rails.