Blueprint MCP Server
Connects an AI agent to a signed-in Blueprint clinician account, exposing tools to list progress notes and note templates, draft and update session notes, sign and lock notes, manage snippets, treatment plans, assessments and worksheets, appointments and external calendars, client transfers and merges, insurance details and claims, payments, superbills, services, fees, and sliding-scale rates.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Blueprint MCP Server List my client's progress notes."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Blueprint MCP server for ChatGPT and Claude
Blueprint documents a Partner Platform API for partner organizations such as EHRs. No official Blueprint MCP server or ChatGPT or Claude connector was found, checked 19 November 2026. Cotlet.dev connects ChatGPT, Claude and other AI agents to your own signed-in Blueprint clinician account.
Source: Blueprint integration page.
What can your agent do?
The live page describes 22 hosted tools: 2 reads and 20 writes. Writes ask for confirmation by default, configurable per tool. Delete and merge actions always require approval. Tools with an action parameter use list and get for reads; other actions write.
list_progress_noteslist_note_templateswrite_session_summaryupdate_session_detailsmagic_edit_noterevert_note_versionsign_and_lock_notemanage_snippetscreate_treatment_planassign_assessments_worksheetsdelete_session_itemsset_session_transcriptscreate_appointmentadd_external_calendartransfer_clientmerge_client_profilesadd_client_insurancemanage_insurance_claimsadd_insurance_paymentmanage_superbillsmanage_services_feesset_sliding_scale_rate
The agent sees the clients your Blueprint role can access. Live recording, dictation, telehealth, your Blueprint users and roles, and your subscription stay outside these tools. Notes start from the session summary or transcript you provide. Review a note before approving its signature.
Related MCP server: clinic-mcp-server
Example requests
List my client's progress notes.
Draft a progress note from the session summary I provide.
Show me the note before asking me to approve signing it.
List insurance claims that need action.
Connect ChatGPT and Claude
Enable Blueprint in the Cotlet.dev console and sign in at https://clinician.blueprint.ai/login in your Cloud Browser.
In ChatGPT, use Settings > Apps & Connectors > Create with
https://cotlet.dev/mcp/v1/connectand OAuth.In Claude, use Settings > Connectors > Add custom connector with the same URL.
Connect Codex and Claude Code
Create an API key in the Cotlet.dev console and set COTLET_API_KEY in your environment.
Codex:
[mcp_servers.cotlet]
url = "https://cotlet.dev/mcp/v1"
bearer_token_env_var = "COTLET_API_KEY"Claude Code:
claude mcp add --transport http cotlet https://cotlet.dev/mcp/v1 --header "Authorization: Bearer $COTLET_API_KEY"Optional local MCP wrapper
Python 3.10+, standard library only. This repository provides seven generic browser helpers over Cotlet.dev: blueprint_guide, blueprint_status, blueprint_open, blueprint_read, blueprint_click, blueprint_type, blueprint_close.
These helpers are separate from the 22 hosted business tools above. Listing helpers needs no key; calling them requires COTLET_API_KEY.
export COTLET_API_KEY="your-key"
python3 blueprint_agent.py serveFor a local MCP client:
{"mcpServers":{"blueprint":{"command":"python3","args":["/absolute/path/to/blueprint_agent.py","serve"],"env":{"COTLET_API_KEY":"your-key"}}}}Other commands: connect, status, guide, read, tools.
The read command opens the browser, reads the page and closes the browser session.
Access and independence
Use your own Blueprint account. You complete sign-in and any verification yourself. Disable Blueprint for agents, reset the browser or change your Blueprint password to revoke access. Cotlet.dev is independent and is not affiliated with, endorsed by or sponsored by Blueprint.
Available Tools
7 toolsblueprint_clickC
Click a numbered element on the current Blueprint page.
Inputs: element (required).
blueprint_closeA
Close the Blueprint browser session when the work is done, so credits stop running.
Inputs: no named parameters.
blueprint_guideA
How to work in Blueprint (work with progress notes, treatment plans, appointments and insurance billing): its screens and the sign-in link. Call this first.
Inputs: task.
blueprint_openB
Open a Blueprint page in your signed-in Cloud Browser (default https://clinician.blueprint.ai/login) to work with work with progress notes, treatment plans, appointments and insurance billing.
Inputs: url.
blueprint_readB
Read the current Blueprint page: its text and numbered buttons, links and fields.
Inputs: element.
blueprint_statusA
Check that your Cotlet.dev account and Blueprint are ready: account, credits and Blueprint connection.
Inputs: no named parameters.
blueprint_typeC
Type text into a numbered field on the current Blueprint page.
Inputs: text (required), element (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 7 tools
Each tool maps to a distinct action in a browser session: open, read, click, type, close, plus guide and status for onboarding/readiness. The boundary between guide (how-to) and status (account/credit check) is clearly stated, and no two tools overlap in operation.
All tools share the blueprint_ prefix and snake_case, with mostly verb-based names (open, read, click, type, close). guide and status are noun-style names, a minor deviation from the otherwise consistent verb pattern.
Seven tools is well-scoped for a browser-automation server targeting a single clinical app. Each tool earns its place: session lifecycle, page interaction, plus two support tools for readiness and guidance.
The surface covers the core browser session lifecycle (open, read, click, type, close) and setup/status, leaving no obvious dead ends. Minor gaps exist, such as explicit navigation/scrolling or waiting tools, but agents can work around these with open and repeated read/click calls.
Related MCP Connectors
SimplePractice MCP server for ChatGPT, Claude and any AI agent: list appointments, accept appointment request, share intake documents, list outstanding balances, list claims, set appointment status and send secure message in your own SimplePractice account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to SimplePractice yourself; Cotlet does not store your password and you need no SimplePractice API key. About the official SimplePractice API: SimplePractice has no public API for practices (checked 27 Oct 2026). Its help center says it does not offer a public-facing API, and the only API, SimpleConnect, lets health plans and employee assistance programs request appointments with in-network clinicians. Setup and FAQ: https://cotlet.dev/integrations/simplepractice-api-mcp-server
Hosted MCP server for Cliniko — patients, appointments, availability, and invoices for AI agents.
Connect ChatGPT or Claude to your CRM, store or shipping API. Keys stay out of the chat.
Connect AI agents to 1000+ apps with managed authentication and tool-calling.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables Claude and other AI assistants to trigger HIPAA-compliant patient task management workflows through natural language.1MIT
- FlicenseAqualityDmaintenanceExposes a clinic's knowledge base and structured records to Claude Desktop as callable tools, with read tools grounded with citations and write tools gated behind approval.4-
- AlicenseAqualityDmaintenanceEnables Claude to access IntakeQ practice management data including scheduling, intake forms, treatment notes, invoices, and client records with HIPAA-compliant audit logging.2244 npm1MIT
- AlicenseNot gradedqualityCmaintenanceEnables LLMs and MCP clients to interact with patient records, encounters, and practice information through tools for clinical, scheduling, messaging, and administrative workflows.MIT