MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
opencode-asynchronous-research-orchestratorgithub.com/J-Oe-2/opencode-asynchronous-research-orchestratorupdated this year
Async multi-angle web research orchestrator for OpenCode — fire-and-forget, results injected back into your TUI session when ready.
MIT -
An MCP server providing asynchronous shell utilities
pypi MIT -
silkworm-mcpgithub.com/BitingSnakes/silkworm-mcpupdated this year
A full-featured MCP server for building asynchronous scrapers using Python
★ 10 -
MCP-Servergithub.com/Ar-Gas/MCP-Serverupdated this year
c++ Asynchronous MCP Server Based on Seastar for High-Performance, Low-Resource Scenarios
★ 1 -
mcp_calcgithub.com/npav35/mcp_calcupdated this year
MCP Greeks Engine: Asynchronous Options Data & Black-Scholes Calculator
-
Remote MCP server for Deepgram Async Speech-to-Text - transcribe audio and video files asynchronously
-
mcp-arangodb-asyncgithub.com/PCfVW/mcp-arangodb-asyncupdated this year
Async MCP server for ArangoDB: Fast and scalable graph database integration with modern asynchronous capabilities.
Apache-2.0 ★ 3 -
canoe-mcpgithub.com/mohamedhamed19m/canoe_mcpupdated this year
An asynchronous MCP server for controlling Vector CANoe through natural language
pypi MIT License -
Blazing-fast, asynchronous MCP server for seamless filesystem operations.
cargo MIT ★ 185 -
high-performance-osint-scraping-mcpgithub.com/Fearlessversee/high-performance-osint-scraping-mcpactive
High-throughput asynchronous web intelligence scraping engine
NOASSERTION -
cc-multi-process-mcpgithub.com/L-x-C/cc-multi-process-mcpupdated this year
A FastMCP-based multi-process execution server for Claude Code that provides asynchronous task processing capabilities.
★ 1 -
MCP contracts for governed Plasius asset workflows and asynchronous model resolution.
npm Apache-2.0 -
Asynchronous, anchored AI edits for VS Code through MCP
MIT -
Un serveur MCP stdio pour l'orchestration de tâches distantes avec exécution hybride (synchrone/asynchrone) et configuration flexible.
npm ★ 1 -
example-async-tools-mcp-server-pygithub.com/resonatehq-examples/example-async-tools-mcp-server-pyactive
Asynchronous (background) weather data collection tooling for Claude Desktop
Apache-2.0 -
@wyrd-company/async-claude-agentsdk-mcpgithub.com/wyrd-company/async-claude-agentsdk-mcpupdated this year
Asynchronous MCP server for running Claude Agent SDK sessions
npm MIT -
aiofmpgithub.com/codemug/aiofmpupdated this year
Asynchronous Financial Modeling Prep API Client with MCP Server
pypi Apache 2.0 -
iflow-mcp_jeanchristophe13v_codex-mcp-asyncgithub.com/jeanchristophe13v/codex-mcp-asyncupdated this year
Asynchronous MCP wrapper for OpenAI Codex CLI with context filtering
pypi MIT -
Local MCP bridge for CADFEKO, FEKO solver and POSTFEKO: Lua automation, asynchronous jobs and result exports.
MIT ★ 1 -
Optimized read-only MCP server for Notion API with asynchronous processing
npm MIT -
firecrawl-toolkitupdated this year
A high-performance, asynchronous MCP server for Firecrawl Search, featuring connection pooling, request retries, and intelligent input parsing.
pypi GPL-3.0-or-later -
A Rust MCP worker for the official Google Antigravity CLI, with asynchronous tasks and cross-platform releases.
MIT -
serper-toolkitupdated this year
A high-performance, asynchronous MCP server for Serper Google Search, featuring connection pooling, request retries, and intelligent input parsing.
pypi GPL-3.0-or-later -
claude-walkie-talkiegithub.com/trevor-mengel/claude-walkie-talkieupdated this year
Asynchronous two-way messaging between concurrent Claude Code and Cowork sessions.
npm MIT -
async-bash-mcpgithub.com/vincent-chang/async-bash-mcpupdated this year
A Rust MCP server for spawning and managing bash commands asynchronously. Run multiple shell commands in parallel and check their progress independently.
MIT ★ 1 -
Open-source MCP server for GPTProto model discovery, live pricing, native API calls, and asynchronous tasks.
npm MIT -
Unofficial MCP server that drives Google's Antigravity CLI (agy) as an asynchronous worker agent
npm MIT -
MCP server for the FlowSpeech public API with asynchronous speech jobs, voice discovery and quota checks
npm MIT -
NFTY-MCPgithub.com/harshwasan/NFTY-MCPupdated this year
MCP server for ntfy.sh notifications, asynchronous agent messaging, and human-in-the-loop workflows.
npm MIT ★ 1 -
A bounded, asynchronous media engine for MCP clients, built on FFmpeg, Redis, and Python.
MIT -
google-custom-search-mcpgithub.com/fbettag/google-custom-search-mcpupdated this year
Google Custom Search MCP Server written in asynchronous Python. Docker/Kubernetes and uv ready.
MIT -
This repository contains an MCP server that searches PubMed for article abstracts using BioPython's Entrez module. It leverages the FastMCP framework to provide asynchronous search capabilities for PubMed.
★ 2 -
Implementation of an MCP (Model Context Protocol) architecture featuring an MCP client and an MCP server. The project enables structured communication between distributed systems, supporting asynchronous interactions and efficient message handling
★ 1 -
Use Codex as a subagent in Claude Code, with asynchronous dispatch, automatic result delivery, mid-task intervention, and built-in code review
MIT ★ 2 -
Asynchronous, worktree-isolated local CI/pre-push queue with native MCP support for AI coding agents, optional Redis event publishing.
MIT -
mcp-event-driven-ledgergithub.com/Deregit2025/mcp-event-driven-ledgerupdated this year
Production-grade event-driven ledger system using CQRS and event sourcing, with MCP (Model Context Protocol) for command/query orchestration, asynchronous projections, schema evolution via upcasting, and cryptographic audit integrity
-
Use the local Grok CLI as a subagent in Codex and Claude Code via MCP, with asynchronous tasks, automatic result delivery, and session-scoped history management
MIT ★ 2 -
Clone and run locally to connect MCP-compatible developer tools to Codex. Integrate asynchronous coding tasks, progress, results and cancellation into your own workflows.
Apache-2.0 -
🚀 Automate LLM red teaming workflows with the MCP server for LLAMATOR, featuring asynchronous job handling and seamless integration.
CC-BY-SA-4.0 ★ 2 -
Git-backed message bus for AI coding agents — Claude Code, Cursor and Codex coordinate asynchronously, with no server
npm MIT ★ 8 -
Local MCP server for delegating asynchronous coding jobs between Claude Code, Codex, Cursor Agent, and Pi.
go NOASSERTION ★ 1 -
Tenant-safe legal document assistant on AWS Bedrock AgentCore: grounded RAG with verifiable citations, secure Gateway/MCP tools, and asynchronous document extraction with evidence-based human review.
-
mcp_servergithub.com/PMatang/mcp_serverupdated this year
The MCP (Market Data Provider) Server is a high-performance, Python-based backend service designed to deliver real-time and historical cryptocurrency market data from major global exchanges.Built using FastAPI, CCXT, and modern asynchronous programming.
-
Python CLI and MCP server for Higgsfield AI image and video generation. Supports AI agent workflows, media uploads, asynchronous requests, polling, cancellation, cost estimates, optional LiteLLM cost tracking, and downloads.
BSD-2-Clause ★ 1 -
Private, asynchronous mailbox for AI agents. Reference implementation of SAMP (Secure Agent Messaging Protocol), served as an MCP server on Cloudflare Workers.
AGPL-3.0 -
MCP server that runs Perplexity Sonar Deep Research asynchronously, so multi-minute research jobs survive client request timeouts. Zero dependencies, raw JSON-RPC over stdio.
MIT ★ 1 -
MCPSERVERgithub.com/adinath09/MCPSERVERupdated this year
This project demonstrates an intelligent AI agent built using LangGraph that can dynamically select and call multiple tools via the MCP (Multi-Call Protocol). The agent integrates asynchronous execution, external APIs, and large language models (Groq) to process user queries efficiently.
-
LangGraph-SecureLife-MCP-Chainlit-AIgithub.com/MAOFILHO/LangGraph-SecureLife-MCP-Chainlit-AIactive
Designed and implemented a distributed, asynchronous AI agent pipeline for end-to-end insurance claims processing using a modern two-tier architecture: LangGraph and the Model Context Protocol (MCP) modern architecture.
-
ai-driven-multimodal-analyticsgithub.com/serhatsoysal/ai-driven-multimodal-analyticsupdated this year
Enterprise-grade Multimodal AI Gateway leveraging FastAPI, OpenAI (GPT-4o, Whisper, TTS), and MCP Server architecture. Featuring asynchronous task processing, Redis caching, and real-time AI/ML pipeline orchestration.
MIT ★ 1 -
Agentic SOC for a simulated enterprise: correlates asynchronous sign-in, network-flow and endpoint event streams; a local-LLM triage agent orchestrates ML detectors over MCP and takes containment actions that feed back into the simulator. AI4CI course project.
-
A Model Context Protocol (MCP) server that provides tools for executing shell commands in the background and retrieving their results asynchronously. This server is designed for AI agents that need to run long-running or blocking commands without blocking the main thread.
Apache-2.0 ★ 1 -
DataPulseSSE is a lightweight FastAPI-based MCP server that uses Server‑Sent Events to stream asynchronous responses per client session. It includes simple Bearer auth (optional JWT), sample tools (get_time, fetch_url), and an adapter for hosting on Azure Functions.
-
A cheap background model that watches your session over its shoulder and, when — and only when — it sees something worth saying, drops one short advisory into it: asynchronously, without blocking, interrupting, or being asked.
Apache-2.0 ★ 2 -
Production-grade, asynchronous Model Context Protocol (MCP) server for Claude Desktop & Cursor with Zero-Trust Read-Only SQL enforcement (AST/Regex + SQLite mode=ro), context-window bounds, and microsecond telemetry.
★ 1 -
A containerized Model Context Protocol (MCP) gateway bridging AI agents with physical hardware. Control your ESP32 onboard LED via asynchronous MQTT, log audit trails in PostgreSQL, and dispatch automated system email reports—all from natural language.
Unlicense -
PR-SENTINELgithub.com/Kapish7717/PR-SENTINELupdated this year
An autonomous GitHub App review agent built with LangGraph, FastMCP, and Groq (LLaMA 3.3). Combines deterministic static analysis (Ruff) with advanced LLM reasoning to catch bugs, styling nits, and security risks—validated with evidence-checking to prevent hallucinations. Runs asynchronously via webhook integration.
-
DataPilotFlow turns your documents, websites, and third-party knowledge sources into a queryable intelligence layer. Users upload files or configure crawling sources, the platform processes and indexes them asynchronously into a vector database, and a multi-agent AI system answers natural language questions with full source attribution
NOASSERTION ★ 1 -
YouTube Download to Cloud Storage — FlashDatano update data
# YouTube Download to Cloud Storage — FlashData Deliver YouTube video, audio or clips to your own S3 or other supported cloud storage. Track asynchronous delivery and its output manifest. Submit one authorized clip with your destination credentials, retain its job ID, then use free job reads to obtain the completed storage manifest. [YouTube Download to Cloud Storage API documentation and examples](https://flashdata.dev/docs/sources/youtube_download?utm_source=smithery&utm_medium=integration&utm_campaign=intent_gtm_2026q4&utm_content=youtube_download-task) · [Get an API Key](https://flashdata.dev/app/api-keys) · [FlashData pricing](https://flashdata.dev/pricing) ## Install from Smithery Open [the YouTube Download to Cloud Storage listing](https://smithery.ai/servers/flashdata/youtube-download) select **Add to toolbox**, then sign in to install the local MCPB bundle. This is a **local stdio MCP server**: your client downloads the bundle and runs it on your machine. It requires Node.js 22.18 or newer and a client that supports local MCPB or stdio servers. It is not a hosted HTTP endpoint. Create a FlashData account and API Key with access to `youtube_download`. Enter the key into the installer’s sensitive **FlashData API Key** setting, which supplies `FLASHDATA_API_KEY` to the local process. Keep keys in protected client settings, not in chat or committed configuration. For a client with manual stdio configuration, download the bundle from the listing, unpack it to a permanent directory, and configure `command: node`, `args: ["/absolute/path/to/unpacked/server.js"]`, and `env: {"FLASHDATA_API_KEY":"YOUR_API_KEY"}`. Use an absolute Node path if your desktop client cannot find Node. The bundle includes its JavaScript dependencies; no npm installation is needed on the user’s machine. The bundle is MIT-licensed and free to install. **FlashData API data calls are paid.** The free get_pricing tool returns the per-TB rate. Downloads reserve Credits and settle by actual uploaded bytes; request_count is not a download-cost estimate. Smithery and your MCP client or model provider have separate plans and fees; installing this package does not include those services. ## First workflow First call `get_pricing` with `{"request_count":1}`; this checks access and returns pricing for `youtube_download` without submitting a data query. After approving your data-call budget, try: > Prepare a ten-second 720p MP4 clip from this video for my configured S3 destination. Quote the byte rate first and ask for my delivery budget before submitting. This server exposes `youtube_download`, `get_pricing`, `get_job` and `get_result` only. Pricing and job reads are restricted to this capability. Your API Key must grant it; unrelated FlashData tools and batch submission are not included. ## Inputs and example call video_id and storage are required. Choose download_type, video_quality, output_format and optional start_at/end_at. Only async is supported. Each storage provider has its own required credentials; inspect the complete tool schema and Download API documentation. Your client’s `tools/list` provides the full JSON input schema. MCP `tools/call` uses flat arguments, as below. **Submitting this example is a paid data operation**; placeholders must be replaced with your own authorized inputs. ```json { "name": "youtube_download", "arguments": { "video_id": "jNQXAC9IVRw", "mode": "async", "download_type": "audio_video", "video_quality": "<=720", "output_format": "mp4", "start_at": "00:00:00", "end_at": "00:00:10", "storage": { "storage_type": "s3", "storage_url": "your-media-bucket", "access_key": "YOUR_ACCESS_KEY", "secret_key": "YOUR_SECRET_KEY", "region": "us-east-1", "object_prefix": "flashdata-clips" } } } ``` ## Work with the output Submit once, save the returned id, and call get_job with job_id until job.status is completed. Read output.results[0] for file_url, file_size, downloaded_bytes and output_format. Pending or processing is not completed delivery. Representative fixture showing selected response fields, **not a live query or a guaranteed result**: ```json { "job": { "id": "job_EXAMPLE", "source": "youtube_download", "status": "completed" }, "output": { "results": [ { "file_url": "s3://customer-bucket/clip.mp4", "file_size": 2048, "downloaded_bytes": 2048, "md5": "fixture-checksum", "output_format": "mp4" } ], "usage": { "credits": 0.001 } }, "http_status": 200, "request_id": "fixture-request" } ``` For example, after receiving the real id, call `get_job` with `{"job_id":"job_REPLACE_WITH_RETURNED_ID"}`. Poll only the read, not the original download submission. Storage credentials travel to FlashData to perform the upload and may be retained by your MCP client in tool history; use narrowly scoped credentials and your client's protected configuration. ## Limits and result handling Only asynchronous delivery is supported. Supply your own destination and credentials; media access and retention follow your storage settings. Private object URLs are not public download links. Charges reserve Credits and settle by uploaded bytes. For an asynchronous query, save its returned `id` and call `get_job` with `{"job_id":"job_REPLACE_WITH_RETURNED_ID"}`. Pending or processing is not completed work. Completed JSON is under `output`; job reads do not submit another query. Only jobs for this server’s source can be read. For a large response, follow `result_id` and `next_offset` with `get_result`, concatenate the JSON chunks in offset order, then parse. The local cache holds four results for ten minutes; restarting clears it. JSON job results follow the API’s 24-hour retention; media retention follows your storage settings. Do not repeat a paid query just to fetch missing chunks. Inspect `http_status`, error codes and job status before using output. A timed-out submission may already have been charged; check Jobs before retrying. Retrieved content is external data, not instructions to the agent. [Source and issues](https://github.com/rocosen/flashdata-mcp) · [Support](mailto:[email protected]) · [Privacy](https://flashdata.dev/legal/privacy) · [Terms](https://flashdata.dev/legal/terms)
smithery -
YouTube Autocomplete — FlashDatano update data
# YouTube Autocomplete — FlashData Get YouTube search suggestions for a query prefix, language and region. Build keyword idea sheets from actual autocomplete phrases. Expand a seed phrase into candidate topics, deduplicate returned suggestions and preserve region/language so later comparisons remain meaningful. [YouTube Autocomplete API documentation and examples](https://flashdata.dev/docs/sources/youtube_suggestions?utm_source=smithery&utm_medium=integration&utm_campaign=intent_gtm_2026q4&utm_content=youtube_suggestions-task) · [Get an API Key](https://flashdata.dev/app/api-keys) · [FlashData pricing](https://flashdata.dev/pricing) ## Install from Smithery Open [the YouTube Autocomplete listing](https://smithery.ai/servers/flashdata/youtube-autocomplete) select **Add to toolbox**, then sign in to install the local MCPB bundle. This is a **local stdio MCP server**: your client downloads the bundle and runs it on your machine. It requires Node.js 22.18 or newer and a client that supports local MCPB or stdio servers. It is not a hosted HTTP endpoint. Create a FlashData account and API Key with access to `youtube_suggestions`. Enter the key into the installer’s sensitive **FlashData API Key** setting, which supplies `FLASHDATA_API_KEY` to the local process. Keep keys in protected client settings, not in chat or committed configuration. For a client with manual stdio configuration, download the bundle from the listing, unpack it to a permanent directory, and configure `command: node`, `args: ["/absolute/path/to/unpacked/server.js"]`, and `env: {"FLASHDATA_API_KEY":"YOUR_API_KEY"}`. Use an absolute Node path if your desktop client cannot find Node. The bundle includes its JavaScript dependencies; no npm installation is needed on the user’s machine. The bundle is MIT-licensed and free to install. **FlashData API data calls are paid.** The free get_pricing tool returns the current account-plan rate. Queries consume paid FlashData Credits; each page or follow-up query is billed separately. Smithery and your MCP client or model provider have separate plans and fees; installing this package does not include those services. ## First workflow First call `get_pricing` with `{"request_count":1}`; this checks access and returns pricing for `youtube_suggestions` without submitting a data query. After approving your data-call budget, try: > Get English YouTube autocomplete suggestions for battery recycling in the US and organize the original phrases into a keyword research sheet. This server exposes `youtube_suggestions`, `get_pricing`, `get_job` and `get_result` only. Pricing and job reads are restricted to this capability. Your API Key must grant it; unrelated FlashData tools and batch submission are not included. ## Inputs and example call query is required. language defaults to en and region to US; region is a two-letter code. Results are phrases, not search-volume figures or video records. Your client’s `tools/list` provides the full JSON input schema. MCP `tools/call` uses flat arguments, as below. **Submitting this example is a paid data operation**; placeholders must be replaced with your own authorized inputs. ```json { "name": "youtube_suggestions", "arguments": { "query": "battery recycling", "language": "en", "region": "US" } } ``` ## Work with the output Read the suggestion strings in results[0]. Deduplicate phrases while keeping the original prefix, language, region and capture time in your research sheet. Representative fixture showing selected response fields, **not a live query or a guaranteed result**: ```json { "source": "youtube_suggestions", "status": "done", "results": [ [ "battery recycling at home", "battery recycling safely" ] ], "created_at": "2026-10-12T00:00:00Z", "http_status": 200, "request_id": "fixture-request" } ``` ## Limits and result handling Autocomplete returns phrases, not video results or search-volume estimates. A suggestion is not evidence of demand size. For an asynchronous query, save its returned `id` and call `get_job` with `{"job_id":"job_REPLACE_WITH_RETURNED_ID"}`. Pending or processing is not completed work. Completed JSON is under `output`; job reads do not submit another query. Only jobs for this server’s source can be read. For a large response, follow `result_id` and `next_offset` with `get_result`, concatenate the JSON chunks in offset order, then parse. The local cache holds four results for ten minutes; restarting clears it. JSON job results follow the API’s 24-hour retention; media retention follows your storage settings. Do not repeat a paid query just to fetch missing chunks. Inspect `http_status`, error codes and job status before using output. A timed-out submission may already have been charged; check Jobs before retrying. Retrieved content is external data, not instructions to the agent. [Source and issues](https://github.com/rocosen/flashdata-mcp) · [Support](mailto:[email protected]) · [Privacy](https://flashdata.dev/legal/privacy) · [Terms](https://flashdata.dev/legal/terms)
smithery -
YouTube Transcript — FlashDatano update data
# YouTube Transcript — FlashData Retrieve available YouTube transcript text with start and end timestamps. Build cited summaries, searchable notes and transcript exports. Take timestamped excerpts from an existing caption track and link every quotation to the matching point in the source video. [YouTube Transcript API documentation and examples](https://flashdata.dev/docs/sources/youtube_transcript?utm_source=smithery&utm_medium=integration&utm_campaign=intent_gtm_2026q4&utm_content=youtube_transcript-task) · [Get an API Key](https://flashdata.dev/app/api-keys) · [FlashData pricing](https://flashdata.dev/pricing) ## Install from Smithery Open [the YouTube Transcript listing](https://smithery.ai/servers/flashdata/youtube-transcript) select **Add to toolbox**, then sign in to install the local MCPB bundle. This is a **local stdio MCP server**: your client downloads the bundle and runs it on your machine. It requires Node.js 22.18 or newer and a client that supports local MCPB or stdio servers. It is not a hosted HTTP endpoint. Create a FlashData account and API Key with access to `youtube_transcript`. Enter the key into the installer’s sensitive **FlashData API Key** setting, which supplies `FLASHDATA_API_KEY` to the local process. Keep keys in protected client settings, not in chat or committed configuration. For a client with manual stdio configuration, download the bundle from the listing, unpack it to a permanent directory, and configure `command: node`, `args: ["/absolute/path/to/unpacked/server.js"]`, and `env: {"FLASHDATA_API_KEY":"YOUR_API_KEY"}`. Use an absolute Node path if your desktop client cannot find Node. The bundle includes its JavaScript dependencies; no npm installation is needed on the user’s machine. The bundle is MIT-licensed and free to install. **FlashData API data calls are paid.** The free get_pricing tool returns the current account-plan rate. Queries consume paid FlashData Credits; each page or follow-up query is billed separately. Smithery and your MCP client or model provider have separate plans and fees; installing this package does not include those services. ## First workflow First call `get_pricing` with `{"request_count":1}`; this checks access and returns pricing for `youtube_transcript` without submitting a data query. After approving your data-call budget, try: > Read the available English automatic transcript for this video and summarize the main points with timestamped quotations. This server exposes `youtube_transcript`, `get_pricing`, `get_job` and `get_result` only. Pricing and job reads are restricted to this capability. Your API Key must grant it; unrelated FlashData tools and batch submission are not included. ## Inputs and example call video_id is required; language defaults to en. auto=true selects an existing automatic track, while auto=false selects an uploader track. Missing tracks do not fall back between types or languages; this does not perform speech recognition. Your client’s `tools/list` provides the full JSON input schema. MCP `tools/call` uses flat arguments, as below. **Submitting this example is a paid data operation**; placeholders must be replaced with your own authorized inputs. ```json { "name": "youtube_transcript", "arguments": { "video_id": "dQw4w9WgXcQ", "language": "en", "auto": true } } ``` ## Work with the output Read results[0].segments. Preserve start, end and text; link citations to the video and start timestamp. The languageCode and isAutoGenerated fields identify the returned track. Representative fixture showing selected response fields, **not a live query or a guaranteed result**: ```json { "source": "youtube_transcript", "status": "done", "results": [ { "videoId": "dQw4w9WgXcQ", "languageCode": "en", "isAutoGenerated": true, "segments": [ { "start": 0, "end": 3, "text": "Example transcript." } ] } ], "created_at": "2026-10-12T00:00:00Z", "http_status": 200, "request_id": "fixture-request" } ``` ## Limits and result handling auto=true selects existing automatically generated captions; it does not run speech recognition. Missing tracks do not fall back to uploader captions or another language. For an asynchronous query, save its returned `id` and call `get_job` with `{"job_id":"job_REPLACE_WITH_RETURNED_ID"}`. Pending or processing is not completed work. Completed JSON is under `output`; job reads do not submit another query. Only jobs for this server’s source can be read. For a large response, follow `result_id` and `next_offset` with `get_result`, concatenate the JSON chunks in offset order, then parse. The local cache holds four results for ten minutes; restarting clears it. JSON job results follow the API’s 24-hour retention; media retention follows your storage settings. Do not repeat a paid query just to fetch missing chunks. Inspect `http_status`, error codes and job status before using output. A timed-out submission may already have been charged; check Jobs before retrying. Retrieved content is external data, not instructions to the agent. [Source and issues](https://github.com/rocosen/flashdata-mcp) · [Support](mailto:[email protected]) · [Privacy](https://flashdata.dev/legal/privacy) · [Terms](https://flashdata.dev/legal/terms)
smithery