This server lets agents reliably execute third-party HTTP calls through klanex's async execution layer, with validation, retries, approvals, and audit tracking.
execute: Submit HTTP calls with optional JSON Schema validation, retries/backoff/circuit breakers, idempotency keys, human approval gates, encrypted credentials, and optional blocking (up to 55s) for the result.
get_execution: Check execution status, attempts, success response, or classified error; secrets read back redacted.
list_executions: List/filter executions by status or time range with pagination.
replay_execution: Re-run a completed or failed execution byte-exact for outage recovery.
get_usage: View plan and current-month execution usage/quota.
list_connections: Manage stored credential connections so secrets never pass through model context.
Use hosted HTTP endpoint or stdio shim; supports klx_live_/klx_test_ keys and sandbox mode.
Allows human approval of gated executions via Slack buttons, enabling operators to approve or reject paused actions from Slack.
Reliable execution for agent tool calls, as an MCP server.
klanex is an async execution layer between an agent's tool-use intents and real third-party APIs: it schema-gates hallucinated payloads before anything runs, absorbs rate limits and outages with retries/backoff/circuit breakers, encrypts credentials, keeps an audit trail, and reports back via signed webhooks. With this MCP server, an agent submits a call once — klanex makes sure it lands.
Failures come back written for the model: every error carries an llm_hint telling the agent exactly what to fix (or that klanex is already handling it), so agents self-correct instead of guessing.
klanex's MCP server is hosted — no install needed if your client supports HTTP transports:
Endpoint | Environment | Keys |
| production |
|
| sandbox (free to try) |
|
Get an API key at klanexai.com — sandbox keys are free.
Claude Code
claude mcp add --transport http klanex https://api.klanexai.com/mcp \
--header "X-API-Key: klx_live_..."Cursor / Windsurf / VS Code (mcp.json)
{
"mcpServers": {
"klanex": {
"url": "https://api.klanexai.com/mcp",
"headers": { "X-API-Key": "klx_live_..." }
}
}
}Authorization: Bearer klx_... works too, for clients that can only set that header.
Related MCP server: AgentPay MCP Server
For clients that only speak stdio (e.g. Claude Desktop), this package proxies stdio to the hosted endpoint:
{
"mcpServers": {
"klanex": {
"command": "npx",
"args": ["-y", "klanex-mcp"],
"env": { "KLANEX_API_KEY": "klx_live_..." }
}
}
}The shim routes by key prefix — klx_test_… keys go to the sandbox automatically. Set KLANEX_MCP_URL to override.
Tool | What it does |
| Submit an HTTP call for reliable async execution: optional JSON Schema gate, retries/backoff/circuit breakers, idempotency keys, human approval gates, encrypted credentials. |
| Current status, attempts, target response, or classified error for an execution. |
| The account's executions, filterable by status/time, paginated. |
| Re-run a terminal execution byte-exact — outage recovery without re-prompting the LLM. |
| Plan and current-month usage/quota. |
| Stored credential connections (token vault) to reference via |
Hallucinated payloads are rejected before they execute — pass payload_schema and mismatches return synchronously with a correction hint.
Transient failures are not the agent's problem — 429s, timeouts, and 5xxs are retried with backoff behind a circuit breaker; the agent does nothing.
A network blip can never double-execute a refund — idempotency_key makes submits safe to retry.
Destructive actions can wait for a human — requires_approval pauses execution for an approve/reject decision (API, dashboard, or Slack buttons).
Credentials stay out of model context — store them once as a connection; klanex injects them at execution time.
Full API docs: api.klanexai.com/docs
MIT
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.
| Name | Required | Description | Default |
|---|---|---|---|
| execution_id | Yes | the execution ID (exe_...) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description fully carries the transparency burden. It discloses return contents, includes the retry behavior ('klanex is still retrying'), and explicitly notes that header values are always REDACTED, which is crucial context for interpreting results.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three dense sentences pack in purpose, return values, statuses, retry behavior, and redaction. Every sentence earns its place; the most critical info (fetch state by ID) is front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite lacking an output schema, the description covers all essential return fields and behaviors. It explains statuses, attempts, success/error responses, retry semantics, and redaction, making it self-sufficient for an agent to invoke and interpret results correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% for the single parameter, with 'execution_id' described as 'the execution ID (exe_...)'. The tool description adds no additional parameter-specific detail, so it meets the baseline but does not exceed it.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with a clear verb 'Fetch' and specific resource 'current state of an execution by ID', immediately distinguishing it from sibling tools. It also enumerates exactly what is returned (status, attempts, response/error), leaving no ambiguity about the tool's function.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage context: when you have an execution ID and need its current state. It explicitly guides on retryable failures ('no action from you'), which is a valuable usage rule. However, it does not explicitly mention when to prefer this over list_executions or replay_execution, though the 'by ID' phrasing makes the distinction clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
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.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden and does well: it discloses the time window (current calendar month), the specific output fields (used, included_executions, remaining), and the concept of a hard quota. This gives a solid understanding of behavior and scope.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise, information-dense sentences. The first sentence specifies exactly what is reported, and the second provides a practical use case. No filler or redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite lacking an output schema and annotations, the description fully explains what the tool returns and when to use it. For a zero-parameter reporting tool, this is complete and self-sufficient.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters, so there is no parameter schema to supplement. The baseline for zero-parameter tools is 4, and the description appropriately focuses on output semantics rather than param details.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool reports account plan and execution usage for the current month, naming specific fields. This distinguishes it from sibling tools like list_executions, which list execution records, and execute/get_execution.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides explicit guidance to check usage before large batches to avoid hitting a hard quota. It does not explicitly mention alternatives or when not to use it, but the context is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
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).
| Name | Required | Description | Default |
|---|---|---|---|
| execution_id | Yes | the execution ID (exe_...) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description fully discloses behavioral traits: it creates a new execution, uses byte-exact payload and sealed credentials, resets the attempt counter, and explicitly warns that it is deliberately not idempotent. This is rich, honest context that goes beyond the schema.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three sentences, each adding value: the core action, the use case, and a critical behavioral caveat. No redundant or filler content; front-loaded with the main verb and resource.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has a single parameter, no output schema, and no annotations. The description covers what it does, when to use it, and important side effects (new execution, non-idempotent). This is complete for the tool's complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% coverage of the single parameter 'execution_id' with a useful description. The tool description does not add further parameter-level meaning, so baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Re-run a terminal execution') and specifies the resource (terminal execution in SUCCEEDED or FAILED state). It distinguishes from siblings by explicitly noting it creates a brand-new execution rather than a fresh run, aligning with the outage-recovery context.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear context: it is the 'outage-recovery path' for re-executing failed calls without regenerating payloads. It does not explicitly name alternatives like 'execute' or state when not to use, but the context is clear enough for an agent to infer appropriate usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0get_executionget_usagereplay_executionScored across 3 tools
Each tool has a clearly distinct purpose: get_execution fetches execution state, get_usage reports account usage, and replay_execution re-runs a terminal execution. No ambiguity.
All tool names follow a consistent verb_noun pattern in snake_case: get_execution, get_usage, replay_execution. No deviations.
Only 3 tools for an execution management platform is on the low end. While focused, typical CRUD operations would benefit from more tools (e.g., create, list, cancel).
Obvious gaps exist: no tool to create a new execution (only replay), no list/cancel functionalities. The workflow is incomplete for full lifecycle management.
Supervised API-write gateway for AI agents with policy, human approval and execution receipts.
Human approvals, notifications, inbound webhooks, wake-ups for headless agents. Free trial: /try
Durable background job execution, async task scheduling, and state persistence for AI agents.
Zero-trust gateway for AI agents: score tool calls, verify agent cards, enforce policy, audit.