Expert skills plus server-side checks for grant writing, home labs and AI agents
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
License key for paid packs (free skills work without it)
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.
Show this caller's license status, unlocked packs and credit balance.
This tool takes no arguments.
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http skillshop https://skillshop.duckdns.org/mcp
Headers
X-Skillshop-Key (optional, not in the config above): License key for paid packs (free skills work without it)Show this caller's license status, unlocked packs and credit balance.
No arguments.
{
"type": "object",
"title": "accountArguments",
"properties": {}
}Check a backup plan against 3-2-1 with tested restores (paid, metered). datasets: [{name, copies: [{type: original|backup|snapshot|raid|sync, location, medium, offsite: bool, encrypted: bool, last_restore_test: 'YYYY-MM-DD'}]}]. Count the original as a copy.
| Argument | Type | Description |
|---|---|---|
| datasets* | array |
{
"type": "object",
"title": "audit_backup_planArguments",
"required": [
"datasets"
],
"properties": {
"datasets": {
"type": "array",
"items": {
"type": "object",
"additionalProperties": true
},
"title": "Datasets"
}
}
}Review a docker-compose file for security and reliability (paid, metered): unpinned images, exposed databases/admin panels, plaintext secrets, Docker socket mounts, privileged containers, missing volumes, restart policies and health checks. Send the whole file as text.
| Argument | Type | Description |
|---|---|---|
| compose_yaml* | string |
{
"type": "object",
"title": "audit_composeArguments",
"required": [
"compose_yaml"
],
"properties": {
"compose_yaml": {
"type": "string",
"title": "Compose Yaml"
}
}
}Check a grant budget's math and rules (paid, metered). budget: {lines: [{category, item, amount, justification, salary?, fte?, months?}], total_request, indirect?: {rate, base: 'tdc'|'mtdc', amount?}, max_indirect_rate?, fringe_rate?, match?: {required_ratio, amount}, participants?}. Checks totals, personnel and fringe math, indirect cap and base, match, missing justifications; returns cost per participant.
| Argument | Type | Description |
|---|---|---|
| budget* | object |
{
"type": "object",
"title": "audit_grant_budgetArguments",
"required": [
"budget"
],
"properties": {
"budget": {
"type": "object",
"title": "Budget",
"additionalProperties": true
}
}
}Review a grant narrative the way a reviewer scores it (paid, metered). sections: {heading: text}. requirements: {required_sections: [..], word_limits: {heading: n}, total_word_limit: n}. request_amount: dollars requested. Returns findings by level (error/warning/nit): missing sections, word limits, unsourced need data, objectives that are not SMART, outputs posing as outcomes, no measurement plan, vague sustainability, request amount mismatch, vague words, placeholders.
| Argument | Type | Description |
|---|---|---|
| sections* | object | |
| requirements | any | |
| request_amount | any |
{
"type": "object",
"title": "audit_grant_proposalArguments",
"required": [
"sections"
],
"properties": {
"sections": {
"type": "object",
"title": "Sections",
"additionalProperties": {
"type": "string"
}
},
"requirements": {
"anyOf": [
{
"type": "object",
"additionalProperties": true
},
{
"type": "null"
}
],
"title": "Requirements",
"default": null
},
"request_amount": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"title": "Request Amount",
"default": null
}
}
}Check a task/handoff record against the agent-handoff protocol (paid, metered). record: {id, owner, state, revision, history[], artifact?, blocker?, delivery?, summary?} Returns ok, errors (protocol breaks), warnings (claims not yet supported by evidence), billing.
| Argument | Type | Description |
|---|---|---|
| record* | object |
{
"type": "object",
"title": "audit_handoffArguments",
"required": [
"record"
],
"properties": {
"record": {
"type": "object",
"title": "Record",
"additionalProperties": true
}
}
}Check a status update before it goes to a person: flags completion claims with no evidence, hedged results, and missing blockers (paid, metered; pairs with the free honest-status skill).
| Argument | Type | Description |
|---|---|---|
| report* | string |
{
"type": "object",
"title": "audit_status_reportArguments",
"required": [
"report"
],
"properties": {
"report": {
"type": "string",
"title": "Report"
}
}
}Load a skill's full instructions by name. Follow them for the current task.
| Argument | Type | Description |
|---|---|---|
| name* | string |
{
"type": "object",
"title": "get_skillArguments",
"required": [
"name"
],
"properties": {
"name": {
"type": "string",
"title": "Name"
}
}
}List every skill and paid check, with pack, price, and whether this caller can use it.
No arguments.
{
"type": "object",
"title": "list_skillsArguments",
"properties": {}
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 20, 2026.
No readOnlyHint / destructiveHint annotations, so clients can't tell a read from a write without asking.
Fix: Add annotations to each tool, e.g. { readOnlyHint: true } for tools that only read.