klanex
Server Details
Reliable async execution for agent tool calls: schema gating, retries, idempotency, audit trail.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- chrassy/klanex-mcp
- GitHub Stars
- 0
- Server Listing
- klanex-mcp
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 6 tools
Each tool targets a distinct concern: creating executions, inspecting a single execution, listing executions, checking quota, managing connections, and replaying a failed execution. Even execute and replay_execution are clearly separated by their recovery-purpose framing.
Tool names mostly follow a verb_noun pattern: get_execution, list_connections, list_executions, replay_execution. 'execute' is a bare verb but is intuitive as the primary action, so the naming remains cohesive and readable.
Six tools is a well-scoped surface for a reliable-execution service: submit, inspect, list, replay, plus usage and connection lookup. Each tool earns its place without redundancy or bloat.
The execution lifecycle is well covered: create, get, list, replay, and usage monitoring. Obvious gaps are connection management (only list is exposed) and lacking an explicit cancel/approval path for the PENDING_APPROVAL status, but core workflows are complete.
Available Tools
6 toolsexecuteAInspect
Submit an HTTP call to a third-party API for reliable asynchronous execution. klanex validates the payload (optionally against payload_schema), stores credentials encrypted, executes with automatic retries/backoff/circuit breakers, and keeps an audit trail — you submit once and never retry transient failures yourself.
Call this instead of making a direct HTTP request whenever the call has side effects (payments, messages, tickets, writes) or the target may be flaky. Prefer connection_id over headers for credentials. Always set idempotency_key for side-effecting calls so resubmitting can never double-execute. Set wait_seconds to block for the result; otherwise poll get_execution with the returned execution_id.
Inputs: url (required), method, headers, payload, +8 more.
get_executionAInspect
Fetch the current state of an execution by ID: status (PENDING_APPROVAL|QUEUED|RUNNING|RETRYING|SUCCEEDED|FAILED), attempts, the target response on success, or a classified error on failure. Retryable failures need no action from you — klanex is still retrying. Header values always read back REDACTED.
Inputs: execution_id (required).
get_usageAInspect
Report the account's plan and execution usage for the current calendar month: used, included_executions, remaining, and whether overage is allowed. Check this before large batches to avoid hitting a hard quota.
list_connectionsAInspect
List the account's stored credential connections (token vault). Reference a ready connection by its ID in execute's connection_id instead of passing raw headers — the credential is injected at execution time and never passes through your context. Secrets are never returned.
list_executionsAInspect
List this account's executions, newest first, optionally filtered by status or a created_at time range. Returns next_cursor when a page is full; pass it back as cursor for the next page.
Inputs: limit, since, until, cursor, +1 more.
replay_executionAInspect
Re-run a terminal (SUCCEEDED or FAILED) execution as a brand-new execution: same target, byte-exact original payload, same sealed credentials, fresh attempt counter. This is the outage-recovery path — failed calls can be re-executed without regenerating the payload. Each call creates a new execution (deliberately not idempotent).
Inputs: execution_id (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Durable background job execution, async task scheduling, and state persistence for AI agents.
Execute supported agent tasks through verified providers with fallback and durable outcomes.
Durable agent-to-agent handoffs and shared scratchpad for multi-agent workflows.
Runtime permission, approval, and audit layer for AI agent tool execution.
Related MCP Servers
- FlicenseNot gradedqualityCmaintenanceEnables AI agents to invoke registered tool skills with strict schema validation, namespace rate limiting, sandboxed execution with timeouts and retries, and SQLite-backed telemetry through a monitoring cockpit.-

polyflowofficial
AlicenseNot gradedqualityBmaintenanceEnables AI agents to run model-checked workflows durably, receiving one work order at a time with guarantees on admission.7 npmApache 2.0- FlicenseNot gradedqualityBmaintenanceEnables AI agents to execute real-world API actions with exactly-once reliability, deduplication, auditing, and human-in-the-loop safeguards via MCP.3-
- AlicenseBqualityBmaintenanceGoverned agent execution gateway for LLM workflows, providing deterministic FSM-based execution, audit trails, and idempotency guarantees via MCP.6146 PyPIMIT
Glama MCP Gateway
Add one secure layer between your agents and this server.