Skillshop
Server Details
Expert skills plus server-side checks for grant writing, home labs and AI agents
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 9 tools
The six audit_* tools each target a clearly distinct artifact (backup plan, compose file, grant budget, grant narrative, handoff record, status report), and list_skills/get_skill/account are separable in purpose. The only soft boundary is between 'paid checks' (the audits) and 'skills' that get_skill loads, which could leave an agent briefly unsure whether a given check is a tool or a skill, though list_skills resolves it.
All names are snake_case and the audit_* family forms a clean, predictable verb_noun cluster alongside list_skills/get_skill. The exception is 'account', a bare noun with no verb, which slightly breaks the convention but remains readable.
Nine tools is well within the sweet spot: two discovery tools (list_skills, get_skill), one account tool, and six narrowly scoped audit checks. Each tool earns its place with no redundant surface.
The read/lookup and per-domain audit lifecycle is covered end to end for an agent-facing marketplace. Gaps are minor: there is no way to purchase or top up credits or unlock a pack (account is read-only), and the set of audits is an ad-hoc catalog rather than a general mechanism, but agents can still complete core workflows.
Available Tools
9 toolsaccountAInspect
Show this caller's license status, unlocked packs and credit balance.
Inputs: no named parameters. Returns: object
audit_backup_planBInspect
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.
Inputs: datasets (required). Returns: object
audit_composeAInspect
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.
Inputs: compose_yaml (required). Returns: object
audit_grant_budgetBInspect
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.
Inputs: budget (required). Returns: object
audit_grant_proposalAInspect
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.
Inputs: sections (required), requirements, request_amount. Returns: object
audit_handoffAInspect
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.
Inputs: record (required). Returns: object
audit_status_reportAInspect
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).
Inputs: report (required). Returns: object
get_skillBInspect
Load a skill's full instructions by name. Follow them for the current task.
Inputs: name (required). Returns: result
list_skillsAInspect
List every skill and paid check, with pack, price, and whether this caller can use it.
Inputs: no named parameters. Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Executable skill packages for agents: vetted competence, ready to run, not just documents.
Human-reviewed security certificates and ops audits for AI agent skills, paid per job.
Live web checks for AI agents: sitemaps, robots.txt, URL status, broken links, feeds, citations.
Agent verification tools: CSV quality, citation checks, AI-readiness audits, requirement extraction
Related MCP Servers
- AlicenseAqualityBmaintenanceResearch methods, workflow tools, and independent review for AI agents, packaged as a Skill, plugin, and local MCP server.9314MIT
- AlicenseAqualityBmaintenanceAI agent workbench and MCP server featuring 35 specialized skills for university student competition proposals, research grants, and scholarship applications.7171MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to index and search local skill libraries, persist and resume task checkpoints, and run validated workflow plans with controlled approval and write permissions.MIT
- AlicenseNot gradedqualityAmaintenanceEnables AI coding providers to run structured multi-agent development workflows, coordinating lead, explorer, consultant, builder, and reviewer roles through server-owned task claims, action logs, handoffs, and health-gated completion. Also provides read-only skills for use cases, specs, triage, consultation, test writing, reviews, and product documentation across Claude Code, Codex CLI, Cursor, Grok Build, and OpenCode.29 npmMIT
Glama MCP Gateway
Add one secure layer between your agents and this server.