Agent exit execution for self-procured services
Dependency-probe-gated exit execution with hash-verified extraction and signed receipts.
Should I use this
Quality & Safety
Findings (2)
- LOWin exit_sweep
- LOWin exit_probe
Based on automated analysis of tool definitions and protocol compliance.
Context Cost
This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.
Install
One-Click Install
Add this to your `claude_desktop_config.json` file:
{
"mcpServers": {
"agent-exit-offboarding-execution": {
"url": "https://textforagents.com/products/agent-exit-offboarding-execution/mcp"
}
}
}Remote endpoints
https://textforagents.com/products/agent-exit-offboarding-execution/mcpstreamable-httpWhat it can do
Tool inventory
Tools (5)
⚪exit_sweep
Portfolio unused-service sweep (Operator plan).
Input Schema
{
"type": "object",
"properties": {}
}⚪exit_probe(service_id)
Dependency probe: SAFE-TO-EXIT / DEPENDENTS-FOUND.
Input Schema
{
"type": "object",
"properties": {
"service_id": {
"type": "string"
}
},
"required": [
"service_id"
]
}⚪exit_execute(service_id, mode)
Execute an exit in the proven order; returns the signed receipt. Metered like the HTTP exit (trial/plan rails only via MCP; paid rails use the HTTP endpoint with x402).
Input Schema
{
"type": "object",
"properties": {
"service_id": {
"type": "string"
},
"mode": {
"type": "string"
}
},
"required": [
"service_id"
]
}⚪exit_verify_receipt(receipt)
Verify an exit receipt's signature.
Input Schema
{
"type": "object",
"properties": {
"receipt": {
"type": "object"
}
},
"required": [
"receipt"
]
}🟢exit_rejoin_check(service_id, scope)
Check whether a COMPLETE exit receipt blocks re-procuring a service.
Input Schema
{
"type": "object",
"properties": {
"service_id": {
"type": "string"
},
"scope": {
"type": "string"
}
},
"required": [
"service_id",
"scope"
]
}Community
Evidence