Photon MCP server for AI agents

Live

OAUTH 2.1

MESSAGING

AI

Photon MCP gives your agent messaging in Photon: send and read Messages over SMS, email, WhatsApp, iMessage, and Telegram, manage Spaces and Users, and handle projects, lines, webhooks, and billing.

  • Per-user credentials: each call uses the actual user's token, never a shared bot.
  • Encrypted per-tenant vault: AES-256, resolved at request time, never in LLM context.
  • Scoped before every call: pre-call scope check, 90-day SIEM-exportable audit chain.
Photon MCP
agent · Acme Q3
Run
List the five most recent messages in my support project.
S
photonmcp_listmessages
118ms
Messaging agent
5 messages in the support project, 3 over iMessage and 2 over SMS. The latest arrived 4 minutes ago.
Sources: Photon support project, 5 messages
photonmcp
5 messages
18:29
Message Claude...

Tools your messaging agent reaches for on Photon, scoped per user.

CALL ANY TOOL
140 tools for messaging in Photon: send and read Messages across SMS, email, WhatsApp, iMessage, and Telegram, manage Spaces and Users, provision lines, and handle webhooks, billing, and 10DLC registration.
photonmcp_assignsmslinecampaign
Assignsmslinecampaign
Assign or replace SMS line campaign Attach a ready campaign from this project’s organization to its line. Requires platforms:write for the project; human and machine actors retain their authenticated identity. Requires a permanent Idempotency-Key and the current assignment version. Provider provisioning runs asynchronously. If the operation fails, its `error` is the problem of one of these codes: `SMS_CAMPAIGN_PROVIDER_REJECTED`, `SMS_CAMPAIGN_RECONCILIATION_REQUIRED`, `SMS_CAMPAIGN_REVOKED`. API reference: https://photon.codes/docs/beta/api-reference/sms-campaigns/assign-or-replace-sms-line-campaign
Parameters
Name
Type
Required
Description
body
object
Required
No description.
path
object
Required
No description.
photonmcp_checkprojectslugavailability
Checkprojectslugavailability
photonmcp_countfilteredverificationcodes
Countfilteredverificationcodes
photonmcp_countusers
Countusers
photonmcp_createorgetspace
Createorgetspace
photonmcp_createtendlccampaign
Createtendlccampaign
photonmcp_deleteproject
Deleteproject
photonmcp_deletevoiceprofileoutbound
Deletevoiceprofileoutbound
photonmcp_getattachment
Getattachment
photonmcp_getdeveloperotelqueryschema
Getdeveloperotelqueryschema
photonmcp_getemailsendingpolicies
Getemailsendingpolicies
photonmcp_getorganizationbillingoverview
Getorganizationbillingoverview
photonmcp_getprojectclosurestatus
Getprojectclosurestatus
photonmcp_getsharedlineassignment
Getsharedlineassignment
photonmcp_gettendlccampaign
Gettendlccampaign
photonmcp_getwebhookdestination
Getwebhookdestination
photonmcp_leaveorganization
Leaveorganization
photonmcp_listdeveloperotellogs
Listdeveloperotellogs
photonmcp_listmessages
Listmessages
photonmcp_listorganizationmembers
Listorganizationmembers
photonmcp_listresourcefilteredverificationcodes
Listresourcefilteredverificationcodes
photonmcp_listtendlccampaignreviewhistory
Listtendlccampaignreviewhistory
photonmcp_listvoiceprofiles
Listvoiceprofiles
photonmcp_listwhatsappaccountphonenumbers
Listwhatsappaccountphonenumbers
photonmcp_provisionimessagededicatedline
Provisionimessagededicatedline
photonmcp_querymessagemetrics
Querymessagemetrics
photonmcp_releasewhatsappsharedlineassignment
Releasewhatsappsharedlineassignment
photonmcp_sendmessage
Sendmessage
photonmcp_unassignvoicelineprofile
Unassignvoicelineprofile
photonmcp_updatetendlcbrand
Updatetendlcbrand

For more tools, view docs.

Build your Agent
Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.
Python · LlamaIndex
import { ScalekitClient } from "@scalekit-sdk/node";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// Photon tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["photonmcp"], toolNames: [
    "photonmcp_listmessages",
    "photonmcp_sendmessage",
    "photonmcp_listspaces"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Show me the latest messages in my support project and send a reply to the newest one" }] });
import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["photonmcp"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Show me the latest messages in my support project and send a reply to the newest one" }],
  tools,
});

// Execute the tool call with the user's vaulted Photon OAuth token
await sk.tools.executeTool(res.choices[0].message.tool_calls[0], "user_123");
import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["photonmcp"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Show me the latest messages in my support project and send a reply to the newest one" }],
  tools,
});

// Tool call runs with the user's vaulted Photon OAuth token
await sk.tools.executeTool(msg.content, "user_123");
import { Agent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["photonmcp"] }, pageSize: 100,
});

const agent = new Agent({
  name: "messaging_agent",
  model: "gemini-2.5-pro",
  instruction: "Photon tools scoped to this user",
  tools,
});

await agent.run("Show me the latest messages in my support project and send a reply to the newest one");
Try these prompts
Copy any prompt into your agent. Each maps directly to a Photon MCP tool. Click to copy, paste into your agent, done.
Messages and Spaces
Copy the prompt
Copied
List the most recent Messages in my project.
Copy the prompt
Copied
Count the Messages in my project from the last 7 days.
Copy the prompt
Copied
List my Spaces and who is in each one.
Projects and lines
Copy the prompt
Copied
List the projects in my organization.
Copy the prompt
Copied
List the resources my project holds.
Copy the prompt
Copied
Check whether the slug acme-support is available for a new project.
Webhooks and billing
Copy the prompt
Copied
List the webhook destinations on my project.
Copy the prompt
Copied
Give me the billing overview for my project.
Copy the prompt
Copied
List my organization's invoices, newest first.
SEE HOW AUTH WORKS
Each user signs in to Photon once, and Scalekit stores and refreshes their tokens. Credentials stay vaulted, every call is scope checked, and every action is logged.
1
Authorize
Your user connects
Photon MCP
once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access
Who:
user ‘A’
when:
Once per user
access:
Limited to user
2
Store
Their
Photon MCP
token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection
vault:
encrypted
scope:
per-user
tokens:
auto-refreshed
3
Resolve
When your agent calls a
Photon MCP
tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs
speed:
~40ms
check:
before every call
seen by:
nobody
4
Audit
Every
Photon MCP
tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it
history:
90 days
export:
SIEM-ready
logged:
every call
Test other agents
See the same per-user auth pattern across other communication connectors.
Engineering Teams
Slack triage
Polls Slack for new messages, classifies bugs and support requests with a LangGraph router, files GitHub issues or Zendesk tickets, and confirms in the thread.
Support and Ops Teams
Support triage agent
Fetches new Zendesk tickets, classifies them by type and urgency, searches the Notion knowledge base for an answer, and routes what it cannot resolve to Slack. Every call runs on the support agent's own delegated OAuth.
Test other agents
See the same per-user auth pattern across other communication connectors.
ENGINEERING
Slack triage agent
Classify new Slack messages as bugs or support requests, file the GitHub issue or Zendesk ticket, and reply in the thread.
SUPPORT
Support triage agent
Classify new Zendesk tickets, search the Notion knowledge base for an answer, and route what it cannot resolve to Slack.
Why Scalekit
Secure your agent's access. Connectors ship in minutes
01.
Shared tokens break per-user analytics
A shared Photon token looks fine in a demo. In production every message send and project change looks like one service account, and you cannot tell which user triggered it. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.
// shared token
audit → bot_service_account

// scalekit
audit → user_abc ✓
02.
Authentication is not authorization
03.
Multi-tenancy is architectural
04.
Photon today. Ten connectors tomorrow.
“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”
Venu Madhav Kattagoni
Head of Engineering / Von
FAQs
Frequently Asked Questions
Does the agent access Photon as the user or through a shared service account?
As the user. Each user signs in to Photon once, and Scalekit stores and refreshes their tokens. Every message, line change, and project update in your audit trail is attributed to that user, not a shared service account.
Where is the Photon OAuth token stored?
In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Credentials never appear in prompts, logs, or LLM context.
Can I limit what the agent does in Photon?
Yes. Filter by tool name in listScopedTools to expose only what you want, for example the list and get tools without photonmcp_sendmessage, photonmcp_deleteproject, or photonmcp_deleteaccount. Scalekit also enforces scope checks before every API call.
What happens when a user revokes Photon access?
The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.
Can the agent send messages and delete projects?
Only if you expose those tools. photonmcp_sendmessage sends SMS, email, WhatsApp, iMessage, or Telegram messages, and photonmcp_deleteproject starts deletion of a project. Leave them out of toolNames to keep the agent to reading Messages, Spaces, and billing.
Start in your coding agent
Up and running in one command
Install the Scalekit skill in your editor of choice. Connector, auth, tools, prompt, all wired up
Claude Code REPL
/plugin marketplace add scalekit-inc/claude-code-authstack
/plugin install agentkit@scalekit-auth-stack
Cursor Code REPL
# ~/.cursor/mcp.json
{
""mcpServers"": {
""photonmcp"": {
""url"": ""https://mcp.scalekit.com/photonmcp"",
""headers"": { ""Authorization"": ""Bearer $SCALEKIT_TOKEN"" }
}
}
}
Codex Code REPL
# ~/.codex/config.toml
[mcp_servers.photonmcp]
url = ""https://mcp.scalekit.com/photonmcp""
auth_env = ""SCALEKIT_TOKEN""
Copilot Code REPL
# .vscode/mcp.json
{
""servers"": {
""photonmcp"": {
""url"": ""https://mcp.scalekit.com/photonmcp"",
""type"": ""http""
}
}
}