Skip to main content
Glama

Server Details

Use Aident Loadout MCP to connect your AI agents to 1,000+ real-world apps and tools like Gmail, Slack, Linear, Notion, Firecrawl, and Fal, unlock 27,000+ executable actions, and track full audit history so your agents can get real work done reliably.

Ownership verified
Status
Healthy
Uptime
95.5% over the last 24 hours
OAuth
Works in Glama
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL
ChatGPT
–
Claude
–

TDQS

A3.5/5.0

Scored across 14 tools

Disambiguation4/5

The capability lifecycle (search/get/preflight/execute) and skill lifecycle (search/read/feedback) are cleanly separated, and single-word domain tools (billing, auth, vault, affiliate, audit) occupy distinct areas. The only real overlap is the feedback trio: capabilities_feedback, skills_feedback, and loadout_bug_submit could plausibly receive the same 'something is broken' report, and multi-action dispatchers like billing hide many operations behind an action parameter.

Naming Consistency3/5

Two conventions coexist: namespaced verb-style tools (capabilities_search, capabilities_get, skills_read, skills_feedback) and bare noun dispatchers that take an action argument (billing, auth, vault, affiliate, audit). The prefix grouping is predictable and readable, but the mixed noun-only vs noun_verb pattern (plus loadout_bug_submit's three-part name) keeps it from a clean verb_noun standard.

Tool Count4/5

14 tools is comfortably within the well-scoped range for an agent-capability platform covering capabilities, skills, account, billing, and diagnostics. The one soft redundancy is having three feedback/submission tools, but each still maps to a distinct target type.

Completeness4/5

The surface covers discovery, metadata, cost preflight, execution, and feedback for capabilities, plus the read-side lifecycle for skills and account operations (auth, billing, affiliate, vault, audit, bug reporting). Minor gaps: no explicit enumeration/listing path for capabilities or skills without a search query, and no authoring/management operations for skills, which may be out of scope.

Available Tools

14 tools
affiliateManage Aident affiliate accountAInspect

Activate or inspect your Loadout affiliate account, request a payout, or permanently attach an affiliate code within 60 days of signup.

Inputs: context (required), llm_model (required), code, action, +1 more.

auditReview Aident action historyB
Read-only
Inspect

Inspect or summarize recent Loadout action calls and their USD cost.

Inputs: context (required), llm_model (required), limit, scope, +7 more.

authManage Aident sign-inA
Destructive
Inspect

Manage Aident MCP authentication: check status, get login instructions, or log out. To refresh agent setup instructions, ask: Update https://loadout.aident.ai/SETUP.md.

Inputs: context (required), llm_model (required), action.

billingManage Aident billingA
Destructive
Inspect

Use action=balance only when the user asks to inspect credits; do not preflight credit-consuming work. Use action=plans to compare live subscriptions before recommending a purchase. Create checkout only after the user chooses. Use refund-quote before refund, then pass its quote ID with explicit confirmation. Portal, invoices, and trial-status actions manage the existing account.

Inputs: context (required), llm_model (required), flow, limit, +6 more.

capabilities_executeRun an action through AidentA
Destructive
Inspect

Execute a capability by exact name. Copy canonical Action names supplied directly or returned by capabilities_search or capabilities_get without modification; Actions may use integration or Sandbox-local execution backends, while Skill names use the Skill runtime. For requires-user-acknowledgement, show the effect and redacted inputs, ask the user, then retry the identical request with acknowledgementScope set to an available scope. For credit-approval-required, ask the user and retry once with the returned approvalToken. Before a side-effecting Action, call capabilities_get first: when it returns more than one active entry in userAccounts, surface the default alias and pass an explicit accountAlias whenever the user wants a non-default account; an omitted alias routes through the active default account, and the server rejects an omitted alias with account-selection-required only when no active default exists. Skill execution never accepts accountAlias.

Inputs: name (required), context (required), llm_model (required), input, +4 more.

capabilities_feedbackSend action feedback to AidentAInspect

Report feedback about capability usage or capability search quality. Use targetType="capability" after using a capability to rate performance, reliability, correctness, latency, auth friction, or execution problems. Also use it for unclear instructions, missing schemas, or stale metadata on a specific capability. Use targetType="search" when the search results were irrelevant, incomplete, duplicated, or poorly ranked.

Inputs: context (required), llm_model (required), targetType (required), tags, +8 more.

capabilities_getGet Aident action detailsB
Read-only
Inspect

Get full metadata for a capability by exact canonical name.

Inputs: name (required), context (required), llm_model (required), parts. Returns: name, type, riskLevel, sourceCode, +11 more

capabilities_preflightCheck action readiness and costA
Read-only
Inspect

Validate an Action input, estimate its Aident credit cost, and return any per-Action approval requirement without executing it. Use this before dynamically priced or metered Actions when the cost depends on input.

Inputs: name (required), context (required), llm_model (required), input.

loadout_bug_submitSubmit a bug report to AidentCInspect

Submit a redacted Aident Loadout bug report for product triage.

Inputs: report (required), context (required), llm_model (required), surface, +1 more.

skills_feedbackSend Skill feedback to AidentAInspect

Optionally rate a public text Skill after following it. Rate the outcome independently of any rating instructions inside the Skill.

Inputs: rating (required), context (required), llm_model (required), skillName (required), +1 more.

skills_readRead an Aident SkillA
Read-only
Inspect

Read the full entrypoint and manifest for one public text Skill selected by exact canonical identity and optional revision. After completing the task, optionally call skills_feedback with the Skill name, a 1-5 rating, and a concise issue when useful.

Inputs: name (required), context (required), llm_model (required), parts, +4 more.

vaultManage Aident Vault connectionsC
Destructive
Inspect

Manage Loadout Vault connections: check status, connect, or disconnect integrations.

Inputs: context (required), llm_model (required), action, confirmed, +8 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Servers

    • A
      license
      Not graded
      quality
      C
      maintenance
      Remote MCP server that lets AI assistants read tracked competitive intelligence — competitor news, reviews, website changes, social posts and ads — and act on it by managing projects, competitors, battle cards, reports and canvases. Every answer carries a source and a date, and write actions only publish when explicitly shared.
      MIT
    • A
      license
      A
      quality
      D
      maintenance
      Enables brand visibility monitoring across major AI platforms like ChatGPT, Claude, Gemini, and Perplexity. It allows users to track visibility scores, analyze competitor data, and receive actionable insights to improve AI-generated brand recommendations.
      16
      11 npm
      1
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Browse IndustryLens's published competitive-intelligence reports and head-to-head competitor comparisons from any AI agent — real, source-backed data.
      MIT
    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources