clinicforagents.com
clinicforagents.com
live
Unverified (seed import)
AI & Agents
11 tools
imperative implementation
Connect Claude, Codex, or OpenClaw. Find what is slowing down your AI helper, get a plan, and retest.
First seen 2026-09-14 · Last seen 2026-09-14 · Source: webmcp.com
Answer 4 · Act 7 · Transact 0 · Score: Not yet scored
Tool inspector
run_agent_physical
act
imperative
Run the six-screen behavioral physical for the checked-in agent. This creates a report in the visible local clinic record.
Page: /
Input schema
| Property | Type | Required | Description |
|---|---|---|---|
goal_drift |
integer | yes | How often does the agent lose the original goal? Use 0 for not seen and 4 for persistent. |
tool_loops |
integer | yes | How often does it repeat a tool call without gaining evidence? Use 0 for not seen and 4 for persistent. |
verification |
integer | yes | How often does it finish without checking the result? Use 0 for not seen and 4 for persistent. |
answer_flips |
integer | yes | How easily does it reverse a supported answer after pushback? Use 0 for not seen and 4 for persistent. |
context_loss |
integer | yes | How often does it forget constraints already provided? Use 0 for not seen and 4 for persistent. |
early_exit |
integer | yes | How often does it stop while safe, in-scope work remains? Use 0 for not seen and 4 for persistent. |
Raw JSON schema
{
"type": "object",
"properties": {
"goal_drift": {
"type": "integer",
"minimum": 0,
"maximum": 4,
"description": "How often does the agent lose the original goal? Use 0 for not seen and 4 for persistent."
},
"tool_loops": {
"type": "integer",
"minimum": 0,
"maximum": 4,
"description": "How often does it repeat a tool call without gaining evidence? Use 0 for not seen and 4 for persistent."
},
"verification": {
"type": "integer",
"minimum": 0,
"maximum": 4,
"description": "How often does it finish without checking the result? Use 0 for not seen and 4 for persistent."
},
"answer_flips": {
"type": "integer",
"minimum": 0,
"maximum": 4,
"description": "How easily does it reverse a supported answer after pushback? Use 0 for not seen and 4 for persistent."
},
"context_loss": {
"type": "integer",
"minimum": 0,
"maximum": 4,
"description": "How often does it forget constraints already provided? Use 0 for not seen and 4 for persistent."
},
"early_exit": {
"type": "integer",
"minimum": 0,
"maximum": 4,
"description": "How often does it stop while safe, in-scope work remains? Use 0 for not seen and 4 for persistent."
}
},
"required": [
"goal_drift",
"tool_loops",
"verification",
"answer_flips",
"context_loss",
"early_exit"
],
"additionalProperties": false
}
Similar websites
cesium-browser-agent.pages.dev
cesium-browser-agent.pages.dev
Cesium Agent Lab
live
Unverified
AI & Agents
flyTo
setView
getView
zoomToExtent
saveViewpoint
Inspect tools
hunchbank.com
hunchbank.com
Let visitors get things done without filling out a single form. Hunch turns every form on your site into a tool visitors can run by chatting in plain English. N…
live
Unverified
AI & Agents
Transact tools
search_1
get_products
search_and_list
extract_page_listings
navigate_flight_search
Inspect tools
sssnack.com
sssnack.com
Agent-made visual feed. Browse, self-register, and publish via MCP or A2A with no connection auth.
live
Unverified
AI & Agents
start_registration
register_agent
recover_agent_token
discover_snacks
search_snacks
Inspect tools
computer.webmcp.com
computer.webmcp.com
WebMCP Computer — one browser machine shared by a human and an agent.
demo
Unverified
AI & Agents
Transact tools
app_open
app_close
app_list
window_focus
window_move
Inspect tools