Source-backed prompting and coding-agent guidance with provenance and freshness checks.
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.
Fetch one allowlisted official documentation page from the curated registry and compare its normalized text with the verified snapshot. Status is unchanged, updated, unavailable (could not be checked now) or unknown (no snapshot). Results are shared by all callers and cached for up to 15 minutes (1 minute when unavailable); live.cached and checked_at show when the page was actually fetched. When the per-source fetch limit is reached, status is unavailable with reason rate_limited. Publication and update dates are never inferred and are always null. Only registry source ids are accepted; no other URL can be requested.
Registry source id, as returned in search_guidance or get_guidance results.
Fetch one allowlisted official documentation page from the curated registry and compare its normalized text with the verified snapshot. Status is unchanged, updated, unavailable (could not be checked now) or unknown (no snapshot). Results are shared by all callers and cached for up to 15 minutes (1 minute when unavailable); live.cached and checked_at show when the page was actually fetched. When the per-source fetch limit is reached, status is unavailable with reason rate_limited. Publication and update dates are never inferred and are always null. Only registry source ids are accepted; no other URL can be requested.
| Argument | Type | Description |
|---|---|---|
| source_id* | string | Registry source id, as returned in search_guidance or get_guidance results. |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"source_id"
],
"properties": {
"source_id": {
"enum": [
"claude-code-practices",
"claude-code-library",
"claude-code-index",
"claude-platform-index",
"claude-prompting",
"codex-prompting",
"openai-skill-authoring",
"openai-plugin-package",
"openai-plugin-skills",
"openai-index",
"openai-api-index",
"codex-index",
"openai-plugin-index",
"openai-eval-skills",
"oai-clear-context",
"oai-reasoning",
"oai-evaluation",
"oai-structured",
"oai-tools",
"oai-untrusted-data",
"oai-cache",
"claude-sonnet-scope",
"claude-progressive",
"claude-tool-descriptions",
"claude-evaluations",
"claude-code-authoring",
"claude-workflow-complexity",
"agentskills-index",
"agentskills-specification",
"agentskills-optimizing-descriptions",
"agentskills-evaluating-skills",
"cursor-index",
"cursor-prompting",
"cursor-plan-mode",
"cursor-models",
"cursor-skills",
"cursor-plugins-reference"
],
"type": "string",
"description": "Registry source id, as returned in search_guidance or get_guidance results."
}
},
"additionalProperties": false
}Return one curated record by its stable id (from search_guidance): provider, canonical source URL, applicability, limitations, labels, the date the source was verified, its snapshot hash and the ledger commit. Unknown ids return an error; nothing is fetched from the web.
| Argument | Type | Description |
|---|---|---|
| id* | string | Stable record id, for example oai-clear-context. |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"id"
],
"properties": {
"id": {
"type": "string",
"pattern": "^[a-z0-9][a-z0-9-]{1,63}$",
"description": "Stable record id, for example oai-clear-context."
}
},
"additionalProperties": false
}List curated guidance records that match a target coding agent, model family, scope and topic. Returns official model guidance, platform documentation and Agent Skills standard records with labels, applicability and the date each source was verified. PromptingCraft.com methodology records are returned only when kind is promptingcraft_methodology and are never official provider guidance. Inputs are fixed categories only. Use get_guidance for the full record.
| Argument | Type | Description |
|---|---|---|
| kind | string | Record kind. Omit for official guidance, platform documentation and standards. |
| limit | integer | Maximum number of results (1-20). |
| scope | string | general: broad provider technique; model_specific: applies only to a named model or interface. |
| topic | string | Guidance topic. |
| model_family | string | Model family the target agent will run, if known. Use other for a family without curated guidance. |
| target_agent | string | Coding agent the prompt is for. |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"kind": {
"enum": [
"model_guidance",
"platform_documentation",
"agent_skills_standard",
"promptingcraft_methodology"
],
"type": "string",
"description": "Record kind. Omit for official guidance, platform documentation and standards."
},
"limit": {
"type": "integer",
"default": 10,
"maximum": 20,
"minimum": 1,
"description": "Maximum number of results (1-20)."
},
"scope": {
"enum": [
"general",
"model_specific",
"any"
],
"type": "string",
"default": "any",
"description": "general: broad provider technique; model_specific: applies only to a named model or interface."
},
"topic": {
"enum": [
"context-and-structure",
"instruction-hierarchy",
"untrusted-content",
"reasoning",
"structured-output",
"tool-use",
"evaluation",
"caching-and-cost",
"scope-control",
"long-context",
"skills-and-plugins",
"agent-workflows",
"planning-and-modes",
"model-selection",
"discovery"
],
"type": "string",
"description": "Guidance topic."
},
"model_family": {
"enum": [
"openai",
"anthropic",
"other",
"any"
],
"type": "string",
"default": "any",
"description": "Model family the target agent will run, if known. Use other for a family without curated guidance."
},
"target_agent": {
"enum": [
"codex",
"claude-code",
"cursor",
"chatgpt",
"any"
],
"type": "string",
"default": "any",
"description": "Coding agent the prompt is for."
}
},
"additionalProperties": false
}