Describe what's going wrong with your AI; get the named technique both of you can read. No auth.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
The minimal executable scaffold: steps (or self-diagnostic for anti-patterns), the narration line to say to your human, and the verification check that proves it worked.
Technique id to apply
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
The minimal executable scaffold: steps (or self-diagnostic for anti-patterns), the narration line to say to your human, and the verification check that proves it worked.
| Argument | Type | Description |
|---|---|---|
| id* | string | Technique id to apply |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"id"
],
"properties": {
"id": {
"type": "string",
"minLength": 1,
"description": "Technique id to apply"
}
},
"additionalProperties": false
}Describe what's going wrong — your human's complaint, or a failure you notice in your own behavior — and get the matching techniques. Deterministic matching; if the description fits two problems it returns one clarifying question instead of guessing.
| Argument | Type | Description |
|---|---|---|
| description* | string | The problem as experienced, in plain words — symptoms, not solution guesses |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"description"
],
"properties": {
"description": {
"type": "string",
"minLength": 1,
"description": "The problem as experienced, in plain words — symptoms, not solution guesses"
}
},
"additionalProperties": false
}Direct lookup by technique id or name, for when you already know what you want. To match by symptom, use classify_intent instead.
| Argument | Type | Description |
|---|---|---|
| query* | string | Technique id (kebab-case) or name, exact or approximate |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"query"
],
"properties": {
"query": {
"type": "string",
"minLength": 1,
"description": "Technique id (kebab-case) or name, exact or approximate"
}
},
"additionalProperties": false
}A technique's mechanism, agent instructions, narration template, verification, and failure modes — the agent-tailored slice. The full human page is linked, not inlined.
| Argument | Type | Description |
|---|---|---|
| id* | string | Technique id, e.g. from classify_intent or find_technique |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"id"
],
"properties": {
"id": {
"type": "string",
"minLength": 1,
"description": "Technique id, e.g. from classify_intent or find_technique"
}
},
"additionalProperties": false
}The eight thinking-failure problems ContextOverflow covers, phrased the way a human experiences them. Start here to see what exists.
No arguments.
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {}
}