Skillshop is an MCP server published by io.github.McCoyLab87, hosted at skillshop.duckdns.org. When last checked on 2026-11-21 it was working: it answers and lists its tools. It declares 9 tools, including list_skills, get_skill, account, audit_handoff, audit_status_report.
Expert skills plus server-side checks for grant writing, home labs and AI agents
23 connections through 4 shared values. Tap any node.
Inferred from the host name and headers: what a server runs on, not who runs it.
List every skill and paid check, with pack, price, and whether this caller can use it.
No parameters.
{
"name": "list_skills",
"description": "List every skill and paid check, with pack, price, and whether this caller can use it.",
"inputSchema": {
"type": "object",
"title": "list_skillsArguments",
"properties": {}
},
"outputSchema": {
"type": "object",
"title": "list_skillsDictOutput",
"additionalProperties": true
}
}Load a skill's full instructions by name. Follow them for the current task.
| Parameter | Type | Description |
|---|---|---|
None yet. Changes appear after a server's second daily check.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
| name * |
| string |
{
"name": "get_skill",
"description": "Load a skill's full instructions by name. Follow them for the current task.",
"inputSchema": {
"type": "object",
"title": "get_skillArguments",
"required": [
"name"
],
"properties": {
"name": {
"type": "string",
"title": "Name"
}
}
},
"outputSchema": {
"type": "object",
"title": "get_skillOutput",
"required": [
"result"
],
"properties": {
"result": {
"type": "string",
"title": "Result"
}
}
}
}Show this caller's license status, unlocked packs and credit balance.
No parameters.
{
"name": "account",
"description": "Show this caller's license status, unlocked packs and credit balance.",
"inputSchema": {
"type": "object",
"title": "accountArguments",
"properties": {}
},
"outputSchema": {
"type": "object",
"title": "accountDictOutput",
"additionalProperties": true
}
}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.
| Parameter | Type | Description |
|---|---|---|
| record * | object |
{
"name": "audit_handoff",
"description": "Check a task/handoff record against the agent-handoff protocol (paid, metered).\n\nrecord: {id, owner, state, revision, history[], artifact?, blocker?, delivery?, summary?}\nReturns ok, errors (protocol breaks), warnings (claims not yet supported by evidence), billing.\n",
"inputSchema": {
"type": "object",
"title": "audit_handoffArguments",
"required": [
"record"
],
"properties": {
"record": {
"type": "object",
"title": "Record",
"additionalProperties": true
}
}
},
"outputSchema": {
"type": "object",
"title": "audit_handoffDictOutput",
"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).
| Parameter | Type | Description |
|---|---|---|
| report * | string |
{
"name": "audit_status_report",
"description": "Check a status update before it goes to a person: flags completion claims with no evidence,\nhedged results, and missing blockers (paid, metered; pairs with the free honest-status skill).",
"inputSchema": {
"type": "object",
"title": "audit_status_reportArguments",
"required": [
"report"
],
"properties": {
"report": {
"type": "string",
"title": "Report"
}
}
},
"outputSchema": {
"type": "object",
"title": "audit_status_reportDictOutput",
"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.
| Parameter | Type | Description |
|---|---|---|
| sections * | object | |
| requirements | any | |
| request_amount | any |
{
"name": "audit_grant_proposal",
"description": "Review a grant narrative the way a reviewer scores it (paid, metered).\n\nsections: {heading: text}. requirements: {required_sections: [..], word_limits: {heading: n},\ntotal_word_limit: n}. request_amount: dollars requested. Returns findings by level (error/warning/nit):\nmissing sections, word limits, unsourced need data, objectives that are not SMART, outputs posing as\noutcomes, no measurement plan, vague sustainability, request amount mismatch, vague words, placeholders.\n",
"inputSchema": {
"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
}
}
},
"outputSchema": {
"type": "object",
"title": "audit_grant_proposalDictOutput",
"additionalProperties": true
}
}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.
| Parameter | Type | Description |
|---|---|---|
| budget * | object |
{
"name": "audit_grant_budget",
"description": "Check a grant budget's math and rules (paid, metered).\n\nbudget: {lines: [{category, item, amount, justification, salary?, fte?, months?}], total_request,\nindirect?: {rate, base: 'tdc'|'mtdc', amount?}, max_indirect_rate?, fringe_rate?,\nmatch?: {required_ratio, amount}, participants?}. Checks totals, personnel and fringe math,\nindirect cap and base, match, missing justifications; returns cost per participant.\n",
"inputSchema": {
"type": "object",
"title": "audit_grant_budgetArguments",
"required": [
"budget"
],
"properties": {
"budget": {
"type": "object",
"title": "Budget",
"additionalProperties": true
}
}
},
"outputSchema": {
"type": "object",
"title": "audit_grant_budgetDictOutput",
"additionalProperties": true
}
}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.
| Parameter | Type | Description |
|---|---|---|
| compose_yaml * | string |
{
"name": "audit_compose",
"description": "Review a docker-compose file for security and reliability (paid, metered): unpinned images,\nexposed databases/admin panels, plaintext secrets, Docker socket mounts, privileged containers,\nmissing volumes, restart policies and health checks. Send the whole file as text.",
"inputSchema": {
"type": "object",
"title": "audit_composeArguments",
"required": [
"compose_yaml"
],
"properties": {
"compose_yaml": {
"type": "string",
"title": "Compose Yaml"
}
}
},
"outputSchema": {
"type": "object",
"title": "audit_composeDictOutput",
"additionalProperties": true
}
}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.
| Parameter | Type | Description |
|---|---|---|
| datasets * | array |
{
"name": "audit_backup_plan",
"description": "Check a backup plan against 3-2-1 with tested restores (paid, metered).\n\ndatasets: [{name, copies: [{type: original|backup|snapshot|raid|sync, location, medium,\noffsite: bool, encrypted: bool, last_restore_test: 'YYYY-MM-DD'}]}]. Count the original as a copy.\n",
"inputSchema": {
"type": "object",
"title": "audit_backup_planArguments",
"required": [
"datasets"
],
"properties": {
"datasets": {
"type": "array",
"items": {
"type": "object",
"additionalProperties": true
},
"title": "Datasets"
}
}
},
"outputSchema": {
"type": "object",
"title": "audit_backup_planDictOutput",
"additionalProperties": true
}
}Skillshop provides expert skills: tested working methods you load on demand. At the start of a task, call list_skills. When a skill's description matches the task, call get_skill and follow its instructions for the rest of the task. If a skill is locked, tell the user plainly what it does and where to get it; do not imitate a locked skill.
Names, descriptions and schemas were written by the server and are shown as data.
Shared addresses on big platforms (Cloudflare, Vercel and the like) put unrelated servers together; those are marked shared_infrastructure. A match is a pivot, not a link between operators.