Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"prosyo": {
"url": "https://app.prosyo.com/ai"
}
}
}
Instant, zero-config Model Context Protocol server connecting AI agents (Claude, Cursor, Windsurf) directly to Prosyo's multichannel B2B outbound engine.
The hosted endpoint is ready. The client config is the URL. There is no API key to create, no developer token to sign up for, and no authentication header to paste. Endpoint: https://app.prosyo.com/ai
The first time Claude or Cursor connects, Prosyo opens an allow screen in the browser so the workspace can be chosen. That confirm is once. It stays out of the config file.
claude_desktop_config.json
{
"mcpServers": {
"prosyo": {
"url": "https://app.prosyo.com/ai"
}
}
}
.cursor/mcp.json
{
"mcpServers": {
"prosyo": {
"url": "https://app.prosyo.com/ai"
}
}
}
~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"prosyo": {
"serverUrl": "https://app.prosyo.com/ai"
}
}
}
.vscode/mcp.json
{
"servers": {
"prosyo": {
"type": "http",
"url": "https://app.prosyo.com/ai"
}
}
}
Install into Claude from the verified Smithery listing.
npx @smithery/cli install hello-kmun/prosyo --client claude
Give me the Prosyo overview: running campaigns, unread replies, and credits.
Draft a four-touch campaign for heads of talent at UK agencies. LinkedIn first, email on day five. Leave it as a draft.
Show unread inbox threads and draft a reply. Do not send it.
The agent calls one public HTTPS endpoint. Prosyo runs LinkedIn, cold email, and the unified inbox behind it. Nothing installs locally.
Read tools return data immediately. Write tools that contact someone or spend credits prepare the action and finish only after confirm_action once the chat says yes. Pause and save-to-list apply immediately.
| Tool | Type | Description |
|---|---|---|
get_overview | Read | Dashboard snapshot: running campaigns, replies, unread inbox, credits, and account health for this Prosyo workspace. |
get_entitlements | Read | Current plan name, trial or paid status, LinkedIn and email seat counts, active campaign limit, and credit balance. |
| Tool | Type | Description |
|---|---|---|
list_campaigns | Read | List campaigns in this workspace. Optional status filter: draft, running, paused, completed, archived. |
get_campaign | Read | Campaign detail: status, enrolled count, sequence step types, and connected seats. |
preview_campaign | Read | Merge a real prospect into the campaign sequence so the messages can be read before launch. |
create_campaign | Write | Create a draft campaign. Does not launch or enroll anyone. Modes: blank, preset, ai, or intent. Stays a draft until a later launch is confirmed. |
launch_campaign | Write | Prepare launching a draft campaign. Sending starts after confirm_action. |
pause_campaign | Write | Pause a running campaign immediately so it stops queueing new sends. Idempotent. |
resume_campaign | Write | Prepare resuming a paused campaign. Sending restarts after confirm_action. |
| Tool | Type | Description |
|---|---|---|
search_prospects | Read | Search people in this workspace by name, company, or email. |
list_lists | Read | Prospect lists with people counts. |
get_prospect_research | Read | Latest research with sources, plus icebreaker, connection note, LinkedIn message, email subject, and body. |
enroll_prospects | Write | Prepare adding a list or specific people to a campaign. Enrollment waits for confirm_action. |
research_prospects | Write | Prepare sourced research and personalised lines. Credits per person. Fresh research is reused free. Runs after confirm. |
enrich_prospects | Write | Prepare enrich-only or a personalised first line. Credits per person. Runs after confirm. |
| Tool | Type | Description |
|---|---|---|
list_inbox | Read | Recent LinkedIn and email conversations. Optional search and unread filter. |
get_thread | Read | One inbox conversation with recent messages. |
draft_reply | Write | Draft an inbox reply. Returns text only. Sending uses send_inbox_reply. |
send_inbox_reply | Write | Prepare a LinkedIn or email reply. The message sends after confirm_action. |
| Tool | Type | Description |
|---|---|---|
get_intent_summary | Read | Tracking status, included people used and left, today's deliveries, High-intent and Warm counts, and the review queue. |
list_intent_leads | Read | People or companies showing buying signals, strongest first, with score, fit, and why now. Locked people show signals only. |
get_intent_lead | Read | One Intent person or company: every signal with source and date, fit reasons, research status, and personalised lines. |
get_ideal_customer | Read | Ideal customer rules: roles, industries, company size, locations, exclusions, and delivery settings. |
list_playbooks | Read | Playbooks and Intent-led audiences: signals watched, Review first or Autopilot, matches, people added, credits used. |
list_review_queue | Read | People a playbook matched who are waiting for approval, or whose researched message is ready to review. |
get_intent_results | Read | Signals by source, people delivered, researched, contacted, replied, meetings, customers, and credits per reply. |
save_intent_leads_to_list | Write | Save unlocked Intent people to a list, with personalised lines. Free. Locked people are skipped. Idempotent. |
unlock_intent_leads | Write | Prepare unlocking locked Intent people. Included people first, then credits. Nothing unlocks until confirm. |
| Tool | Type | Description |
|---|---|---|
approve_review | Write | Prepare approving people in the review queue. Approval researches them for credits. The message is still visible before send. |
confirm_action | Write | Run a launch, enroll, resume, inbox send, unlock, research, enrichment, or review approval after an explicit yes in chat. Pass the confirmation token from the previous tool. |
Prosyo is published as io.github.ShubhamTuts/prosyo version 1.0.1. The record lives in server.json and points at https://app.prosyo.com/ai over Streamable HTTP, with no API key and no auth headers.
The Model Context Protocol Registry is the community index of public MCP servers. The Model Context Protocol organization on GitHub runs it collaboratively, backed by Anthropic, GitHub, Microsoft, and PulseMCP. The service is modelcontextprotocol/registry. Reference servers live in modelcontextprotocol/servers. Clients and other registries read that upstream metadata.