agentic-orchestration (zlatko-lakisic/agentic-orchestration) is an MCP server listed on the M8ven Trust Index. It scores 26 out of 100, grade F. It declares 29 tools. No publisher has claimed this listing.

Warning

26/100

agentic-orchestration

Item: agentic-orchestration
Rating: 26
Author: M8ven

Model-agnostic multi-agent orchestration built on CrewAI. YAML-driven agent and MCP catalogs, dynamic LLM planning, sessions, and pluggable execution — mix Ollama, OpenAI, Anthropic, HuggingFace, and your own tools without rewriting orchestration logic.

→ zlatko-lakisic/agentic-orchestration · listed on github_repo_search

Warning. Serious findings were identified. Review the full report before connecting. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

Code Verified⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every push why connect →

Who stands behind it

zlatko-lakisic

Source: github_repo_search

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

⚡ Connect GitHub for Live Monitored

Install from

GitHub

The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.

// key findings

🚨

Secret credentials may flow to a network call

1 flow detected: OPENAI_API_KEY. We can’t prove the destination matches the brand the credential belongs to.

🚨

Reads files from sensitive locations

Touches: /.dockerenv

🚨

Code appears obfuscated

6 files are unreadable to a human reviewer. Cannot audit what they do.

🔐

You'll be asked for 8 credentials: AGENTIC_CHAT_COMPLETIONS_API_KEY, AGENTIC_ORCHESTRATE_API_KEY, ANTHROPIC_API_KEY, OLLAMA_API_KEY, OPENAI_API_KEY, AGENTIC_SPEECH_TOKEN, JETSTREAM_API_KEY, VLLM_API_KEY

These are read from process.env at runtime. Make sure you trust where they’ll be sent.

// tools this server exposes29 tools

These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.

describe_image_file

Describe a local image file with a vision model.

transcribe_audio_file

Transcribe speech from a local audio file (mp3/wav/m4a/ogg/…).

analyze_video_file

Sample frames from a local video and summarize what is shown.

detect_objects

Detect objects; returns JSON with detections[], image{}, model{}.

get_plant_profile

Exact lookup by scientific or common name (case-insensitive).

search_plants

Keyword search over common_name, scientific_name, and notes (deterministic).

get_water_requirement_mm

Compute weekly irrigation need in mm: plant_factor_midpoint × et0_mm_per_week.

get_usda_zone

Return the USDA Plant Hardiness Zone temperature band for a zone like 7a.

resolve_zone_from_temp

Map a Fahrenheit temperature to the matching USDA hardiness zone band.

list_reference_et0

List representative peak-season reference ET0 values by climate_setting.

describe_dataset

Return provenance metadata: authoritative vs curated vs representative files, row counts, and an explicit note that the plant list is a seed set, not full WUCOLS.

delegatetask

fetchurl

listalloweddirectories

listdirectory

readfile

readtextfile

writefile

createdirectory

editfile

getfileinfo

searchfiles

directorytree

k8sdelegatetask

ragquery

societypost

societyreadthread

societylistagents

runterminalcommand

// environment variables

To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.

configAGENTIC_AGENT_PROVIDERS_CATALOG

configAGENTIC_AMD_HOST_METRICS_PATH

configAGENTIC_API_TOKENS_DIR

🔐 secretAGENTIC_CHAT_COMPLETIONS_API_KEY

configAGENTIC_CHAT_COMPLETIONS_CORS_ORIGIN

configAGENTIC_CHAT_COMPLETIONS_VERBOSE_CREW

configAGENTIC_EDGE_HOSTNAME

configAGENTIC_EDGE_PLATFORM

configAGENTIC_EXAMPLE

configAGENTIC_EXECUTION_BACKENDAGENTIC_EXECUTION_BACKEND (inprocess, subprocess, kubernetes), AGENTIC_SUBPROCESS_WORKERS, AGENTIC_K8S_, warm pool, delegation

configAGENTIC_EXTRA_AGENT_PROVIDERS_CATALOG_DIRS

configAGENTIC_EXTRA_MCP_PROVIDERS_PATHAGENTIC_EXTRA_MCP_PROVIDERS_PATH, HOME_ASSISTANT_URL, HOME_ASSISTANT_TOKEN, search keys as documented in example

configAGENTIC_HOST_METRICS_PROC_ROOT

configAGENTIC_IRRIGATION_MAX_TOKENS

configAGENTIC_JETSON_ENABLE_ENGINE

configAGENTIC_JETSON_JTOP_METRICS_PATH

configAGENTIC_K8S_DELEGATION_ENABLED

configAGENTIC_K8S_WARM_POOL_ENABLED

configAGENTIC_KBAGENTIC_LEARNING, AGENTIC_LEARNING_EVAL, AGENTIC_EVAL_MODEL, AGENTIC_KB, AGENTIC_KB_MAX_HITS, …

configAGENTIC_LOGISTICS_SIM_MCP_PY

configAGENTIC_MCP_FETCH_ENABLED

configAGENTIC_MCP_MEDIA_ENABLED

configAGENTIC_MCP_MEMORY_MCP_ENABLED

configAGENTIC_NVIDIA_HOST_METRICS_PATH

configAGENTIC_OLLAMA_KEEPALIVE_ATTEMPTS

configAGENTIC_OLLAMA_KEEPALIVE_INTERVAL_MS

configAGENTIC_OLLAMA_KEEP_ALIVE

configAGENTIC_OLLAMA_MODE

configAGENTIC_OLLAMA_RUNTIME

configAGENTIC_OPENAI_API_DISABLE_CACHE

configAGENTIC_OPENAI_PROXY_DYNAMIC_AGENT_PROVIDER_IDS

configAGENTIC_OPENAI_PROXY_FETCH_IMAGE_DENY_PRIVATE_NETWORKS

configAGENTIC_OPENAI_PROXY_FETCH_IMAGE_TIMEOUT_MS

configAGENTIC_OPENAI_PROXY_FETCH_IMAGE_URLS

configAGENTIC_OPENAI_PROXY_FETCH_MEDIA_URLS

configAGENTIC_OPENAI_PROXY_ORCHESTRATOR_SESSION_RESET

🔐 secretAGENTIC_ORCHESTRATE_API_KEY

configAGENTIC_ORCHESTRATOR_CONTEXT_FILE

configAGENTIC_PLANNER_MODELAGENTIC_PLANNER_MODEL (e.g. openai/..., anthropic/..., ollama/...), AGENTIC_PLANNER_USE_LITELLM, AGENTIC_PLANNER_MAX_STEPS, AGENTIC_PLANNER_JSON_MODE, AGENTIC_PLANNER_REPAIR_RETRY, AGENTIC_PLANNER_429_RETRIES, AGENTIC_PLANNER_CONTEXT_TURNS, AGENTIC_PLANNER_MESSAGE_CHARS

configAGENTIC_PYTHONAGENTIC_WEB_HOST, AGENTIC_WEB_PORT, AGENTIC_TOOL_ROOT, AGENTIC_PYTHON, AGENTIC_WEB_PROSE_DELIVERABLE — in agentic-orchestration-web/.env

configAGENTIC_REQUIRE_IDENTITY

configAGENTIC_RUN_STORE_PATH

configAGENTIC_SERVE_HOST

configAGENTIC_SERVE_MCP_TUNNEL

configAGENTIC_SERVE_PORT

configAGENTIC_SERVE_SESSION_OVERLAY

configAGENTIC_SERVE_TLS_CA_FILE

configAGENTIC_SERVE_TLS_CERTFILE

configAGENTIC_SERVE_TLS_KEYFILE

configAGENTIC_SPEECH_ADVERTISE_STT_URL

configAGENTIC_SPEECH_ADVERTISE_TTS_URL

configAGENTIC_SPEECH_ENABLED

configAGENTIC_SPEECH_STT_HOST

configAGENTIC_SPEECH_STT_PORT

configAGENTIC_SPEECH_STT_URL

configAGENTIC_SPEECH_TTS_HOST

configAGENTIC_SPEECH_TTS_PORT

configAGENTIC_SPEECH_TTS_URL

configAGENTIC_SUBPROCESS_LOG_TO_CONSOLE

configAGENTIC_TOOL_ROOTAGENTIC_WEB_HOST, AGENTIC_WEB_PORT, AGENTIC_TOOL_ROOT, AGENTIC_PYTHON, AGENTIC_WEB_PROSE_DELIVERABLE — in agentic-orchestration-web/.env

configAGENTIC_WEB_AUTO_INSTALL_REQUIREMENTS

configAGENTIC_WEB_AVATAR_HEADER

configAGENTIC_WEB_DEFAULT_RUN_MODE

configAGENTIC_WEB_HOSTOpen http://127.0.0.1:3847/ by default. For LAN access, set =0.0.0.0 in agentic-orchestration-web/.env.

configAGENTIC_WEB_HOST_METRICS_PUSH_MS

configAGENTIC_WEB_PERSIST_UPLOADS

configAGENTIC_WEB_PLANNER_GREET

configAGENTIC_WEB_PORTHost/port are read from AGENTIC_WEB_HOST / in that folder’s .env unless you override on the command line.

configAGENTIC_WEB_SESSION_ID_HEADER

configAGENTIC_WEB_USER_NAME_HEADER

configAGENTIC_WEB_WELCOME_MESSAGE

🔐 secretANTHROPIC_API_KEYANTHROPIC_API_KEY, ANTHROPIC_BASE_URL

configHOSTNAME

configKUBERNETES_SERVICE_HOST

configKUBERNETES_SERVICE_PORT

configOLLAMA_API_BASE

🔐 secretOLLAMA_API_KEY

configOLLAMA_HOSTOLLAMA_HOST, ROUTER_OLLAMA_MODEL

configOPENAI_API_BASE

🔐 secretOPENAI_API_KEYOPENAI_API_KEY, OPENAI_BASE_URL, OPENAI_MODEL_NAME

configOPENAI_BASE_URLOPENAI_API_KEY, OPENAI_BASE_URL, OPENAI_MODEL_NAME

configAGENTIC_MCP_DETECTION_ENABLED

configAGENTIC_MCP_DETECTION_DEFAULT_PROVIDER

configAGENTIC_DETECTION_DEFAULT_PROVIDER

configDATA_DIR

configHOST

configAGENTIC_VERIFY

configAGENTIC_RUN_ID

configROUTER_OLLAMA_MODELOLLAMA_HOST, ROUTER_OLLAMA_MODEL

configAGENTIC_DYNAMIC_ITERATIVE_ROUNDS

configAGENTIC_DYNAMIC_ITERATIVE_MAX_ROUNDS

configAGENTIC_DYNAMIC_ITERATIVE_MIN_ROUNDS

configAGENTIC_EXEC_QUEUE_PRIORITY

configAGENTIC_HARNESS_TIER

configAGENTIC_EDGE_PLATFORM_LOG

configAGENTIC_APP_ID

configAGENTIC_USER_ID

configAGENTIC_USER_NAME

configAGENTIC_CLIENT_IP

configAGENTIC_API_TOKEN_ID

configAGENTIC_ANSWER_CACHEAnswer cache

configAGENTIC_DYNAMIC_ITER_STREAM_STEPS

configAGENTIC_OLLAMA_NUM_PARALLEL

configOLLAMA_NUM_PARALLEL

configAGENTIC_MCP_CREDENTIAL_SKIP_VERBOSE

configAGENTIC_MCP_CREDENTIAL_SKIP_SUMMARY_AT

configAGENTIC_MCP_STDIO_HANDSHAKE

configAGENTIC_MCP_STDIO_HANDSHAKE_TIMEOUT

configAGENTIC_CREWAI_MCP_TOOLS_LIST_HOTFIX

configAGENTIC_K8S_ALLOW_STDIO_MCPS

configAGENTIC_K8S_POD_SIDECAR_MCPS

configAGENTIC_K8S_EXTRA_HTTP_MCPS

configAGENTIC_K8S_WORKER_STDIO_MCPS

configAGENTIC_K8S_SUPERGATEWAY_STATEFUL

configAGENTIC_VIDEO_FFMPEG

configAGENTIC_VIDEO_FFPROBE

configAGENTIC_MEDIA_VISION_MODEL

configAGENTIC_VIDEO_VISION_MODEL

configAGENTIC_MEDIA_WHISPER_MODEL

configAGENTIC_MEDIA_TRANSCRIBE_MODEL

configAGENTIC_VIDEO_FRAME_COUNT

configAGENTIC_FETCH_URL_MAX_CHARS

configAGENTIC_CUSTOM_TOOL_SANDBOX

configAGENTIC_CUSTOM_TOOL_MAX_UPLOAD_BYTES

configAGENTIC_CUSTOM_TOOL_MAX_FS_ROOTS

configAGENTIC_TOOL_PORT

configAGENTIC_TOOL_RESULT_CHARS

configAGENTIC_SPEECH_WHISPER_MODEL

configAGENTIC_SPEECH_WHISPER_DEVICE

configAGENTIC_SPEECH_WHISPER_COMPUTE

configAGENTIC_SPEECH_WHISPER_BEAM

🔐 secretAGENTIC_SPEECH_TOKEN

configCOMSTAR_SHERPA_TTS_DIR

configAGENTIC_SPEECH_TTS_THREADS

configAGENTIC_SPEECH_TTS_PROVIDER

configANTHROPIC_API_URL

configAGENTIC_DISABLE_MCP_TOOL_HINT

configHUGGINGFACE_API_BASEHF_TOKEN, HUGGINGFACE_API_BASE

🔐 secretJETSTREAM_API_KEY

configAGENTIC_OLLAMA_VERBOSE

configAGENTIC_OLLAMA_MAX_ITER

configAGENTIC_OLLAMA_PULL_PROGRESS_STDERR

configAGENTIC_OLLAMA_SERVE_DEBUG

configOLLAMA_KEEP_ALIVE

configAGENTIC_OLLAMA_IDLE_UNLOAD_SECONDS

🔐 secretVLLM_API_KEY

configOPENAI_MODEL_NAMEOPENAI_API_KEY, OPENAI_BASE_URL, OPENAI_MODEL_NAME

configAGENTIC_HARNESS_SKIP_SELFCONTAINED_INIT

configAGENTIC_HARNESS_EVAL

configAGENTIC_HARNESS_EVAL_MODEL

configAGENTIC_HARNESS_RECORD_STATS

configAGENTIC_SKILLS_MAX_CHARS_PER_TASK

configAGENTIC_ATTACHMENTS_ALLOW_ABSOLUTE

configAGENTIC_VIDEO_EXTRACT_FRAMES

configAGENTIC_CREDENTIAL_SKIP_VERBOSE

configAGENTIC_CREDENTIAL_SKIP_SUMMARY_AT

configAGENTIC_CLOUD_PROVIDER_TYPES

configAGENTIC_ANONYMIZE_VISION_MODEL

configAGENTIC_ANONYMIZE_NER_ENTITIES

configCREWAI_TESTING

configCREWAI_TRACING_ENABLED

configAGENTIC_DEAL_AUTH

configAGENTIC_DETECTION_ARTIFACT_CACHE

configAGENTIC_DETECTION_PREVIEW_MAX_EDGE

configAGENTIC_DETECTION_PREVIEW_MAX_BYTES

configAGENTIC_OLLAMA_CHAT_TIMEOUT_SEC

configAGENTIC_DIRECT_AGENT_CONTEXT_CHARS

configAGENTIC_PLANNER_PROGRESS_LOG

configAGENTIC_ORCHESTRATOR_CONTEXT

configAGENTIC_PLANNER_DEBUG

configAGENTIC_PLANNER_DEBUG_CHARS

configAGENTIC_PLANNER_USE_LITELLMAGENTIC_PLANNER_MODEL (e.g. openai/..., anthropic/..., ollama/...), AGENTIC_PLANNER_USE_LITELLM, AGENTIC_PLANNER_MAX_STEPS, AGENTIC_PLANNER_JSON_MODE, AGENTIC_PLANNER_REPAIR_RETRY, AGENTIC_PLANNER_429_RETRIES, AGENTIC_PLANNER_CONTEXT_TURNS, AGENTIC_PLANNER_MESSAGE_CHARS

configAGENTIC_PLANNER_JSON_MODEAGENTIC_PLANNER_MODEL (e.g. openai/..., anthropic/..., ollama/...), AGENTIC_PLANNER_USE_LITELLM, AGENTIC_PLANNER_MAX_STEPS, AGENTIC_PLANNER_JSON_MODE, AGENTIC_PLANNER_REPAIR_RETRY, AGENTIC_PLANNER_429_RETRIES, AGENTIC_PLANNER_CONTEXT_TURNS, AGENTIC_PLANNER_MESSAGE_CHARS

configAGENTIC_PLANNER_TIMEOUT_SEC

configAGENTIC_PLANNER_429_RETRIESAGENTIC_PLANNER_MODEL (e.g. openai/..., anthropic/..., ollama/...), AGENTIC_PLANNER_USE_LITELLM, AGENTIC_PLANNER_MAX_STEPS, AGENTIC_PLANNER_JSON_MODE, AGENTIC_PLANNER_REPAIR_RETRY, AGENTIC_PLANNER_429_RETRIES, AGENTIC_PLANNER_CONTEXT_TURNS, AGENTIC_PLANNER_MESSAGE_CHARS

configAGENTIC_PLANNER_CONTEXT_TURNSAGENTIC_PLANNER_MODEL (e.g. openai/..., anthropic/..., ollama/...), AGENTIC_PLANNER_USE_LITELLM, AGENTIC_PLANNER_MAX_STEPS, AGENTIC_PLANNER_JSON_MODE, AGENTIC_PLANNER_REPAIR_RETRY, AGENTIC_PLANNER_429_RETRIES, AGENTIC_PLANNER_CONTEXT_TURNS, AGENTIC_PLANNER_MESSAGE_CHARS

configAGENTIC_PLANNER_MESSAGE_CHARSAGENTIC_PLANNER_MODEL (e.g. openai/..., anthropic/..., ollama/...), AGENTIC_PLANNER_USE_LITELLM, AGENTIC_PLANNER_MAX_STEPS, AGENTIC_PLANNER_JSON_MODE, AGENTIC_PLANNER_REPAIR_RETRY, AGENTIC_PLANNER_429_RETRIES, AGENTIC_PLANNER_CONTEXT_TURNS, AGENTIC_PLANNER_MESSAGE_CHARS

configAGENTIC_PLANNER_SINGLE_AGENT_LLM

configAGENTIC_AGI_TRAITS

configAGENTIC_ORCHESTRATOR_EXCERPT_CHARSAGENTIC_ORCHESTRATOR_SESSION, AGENTIC_ORCHESTRATOR_DEFAULT_SESSION, AGENTIC_ORCHESTRATOR_MAX_PLANNER_TURNS, AGENTIC_ORCHESTRATOR_EXCERPT_CHARS, …

configAGENTIC_WEB_USER_DISPLAY_NAME

configAGENTIC_ORCHESTRATOR_TASK_DESC_CHARS

configAGENTIC_ORCHESTRATOR_TASK_OUTPUT_CHARS

configAGENTIC_STRICT_MCP_IDS

configAGENTIC_STRICT_SKILL_IDS

configAGENTIC_DISABLE_MCP_GOAL_MATCH

configAGENTIC_DISABLE_SKILL_GOAL_MATCH

configAGENTIC_HARDWARE_FILTER_QUIET

configAGENTIC_PLANNER_MAX_STEPSAGENTIC_PLANNER_MODEL (e.g. openai/..., anthropic/..., ollama/...), AGENTIC_PLANNER_USE_LITELLM, AGENTIC_PLANNER_MAX_STEPS, AGENTIC_PLANNER_JSON_MODE, AGENTIC_PLANNER_REPAIR_RETRY, AGENTIC_PLANNER_429_RETRIES, AGENTIC_PLANNER_CONTEXT_TURNS, AGENTIC_PLANNER_MESSAGE_CHARS

configAGENTIC_PLANNER_REPAIR_RETRYAGENTIC_PLANNER_MODEL (e.g. openai/..., anthropic/..., ollama/...), AGENTIC_PLANNER_USE_LITELLM, AGENTIC_PLANNER_MAX_STEPS, AGENTIC_PLANNER_JSON_MODE, AGENTIC_PLANNER_REPAIR_RETRY, AGENTIC_PLANNER_429_RETRIES, AGENTIC_PLANNER_CONTEXT_TURNS, AGENTIC_PLANNER_MESSAGE_CHARS

configAGENTIC_ITERATIVE_CONTROLLER_EXCERPT_CHARS

configAGENTIC_LEARNING_EVALAGENTIC_LEARNING, AGENTIC_LEARNING_EVAL, AGENTIC_EVAL_MODEL, AGENTIC_KB, AGENTIC_KB_MAX_HITS, …

configAGENTIC_ITERATIVE_CONTROLLER_MODEL

configAGENTIC_EVAL_GOAL_CHARS

configAGENTIC_EVAL_OUTPUT_CHARS

configAGENTIC_FINAL_QA

configAGENTIC_QA_GOAL_CHARS

configAGENTIC_QA_OUTPUT_CHARS

configAGENTIC_MCP_PROVIDERS_CATALOG

configAGENTIC_AGENT_SKILLS_CATALOG

configAGENTIC_RAG_SOURCES_CATALOG

configAGENTIC_EXEC_FALLBACK_PROVIDER_ID

configAGENTIC_EXEC_FALLBACK_REPLACE_ANY_HF

configAGENTIC_EXEC_QUEUE_BACKEND

configAGENTIC_EXEC_QUEUE_CPU_CORES

configAGENTIC_EXEC_QUEUE_VRAM_GB

configAGENTIC_EXEC_QUEUE_AUTOSCALE_ENABLED

configAGENTIC_EXEC_QUEUE_AUTOSCALE_MIN_REPLICAS

configAGENTIC_EXEC_QUEUE_AUTOSCALE_MAX_REPLICAS

configAGENTIC_EXEC_QUEUE_AUTOSCALE_SLOTS_PER_WORKER

configAGENTIC_EXEC_QUEUE_AUTOSCALE_UP_THRESHOLD

configAGENTIC_EXEC_QUEUE_AUTOSCALE_DOWN_COOLDOWN_SECONDS

configAGENTIC_K8S_NAMESPACE

configAGENTIC_K8S_WARM_POOL_DEPLOYMENT

configAGENTIC_EXEC_QUEUE_FAIR_SHARE_ENABLED

configAGENTIC_EXEC_QUEUE_PREEMPT_ENABLED

configAGENTIC_EXEC_QUEUE_PREEMPT_THRESHOLD

configAGENTIC_EXEC_QUEUE_PREEMPT_MIN_GAP

configAGENTIC_EXEC_QUEUE_PREEMPT_PROTECT_SECONDS

configAGENTIC_WEB_PROSE_DELIVERABLEChat answers are prose by default (not raw JSON): the web server sets =1 for orchestrator runs, and the UI unwraps any JSON-shaped agent output before rendering.

configAGENTIC_AVAILABLE_ARCHITECTURESAGENTIC_AVAILABLE_ARCHITECTURES, AGENTIC_ASSUME_GPU, AGENTIC_ASSUME_TPU, AGENTIC_ASSUME_VRAM_GB, AGENTIC_MAX_VRAM_FRACTION, AGENTIC_MAX_VRAM_GB, AGENTIC_DISABLE_HARDWARE_FILTER, …

configCOLAB_TPU_ADDR

configTPU_NAME

configTPU_WORKER_ID

configXRT_TPU_CONFIG

configLIBTPU_INIT_ARGS

configPJRT_DEVICE

configAGENTIC_VRAM_HEURISTICS

configAGENTIC_MAX_VRAM_FRACTIONAGENTIC_AVAILABLE_ARCHITECTURES, AGENTIC_ASSUME_GPU, AGENTIC_ASSUME_TPU, AGENTIC_ASSUME_VRAM_GB, AGENTIC_MAX_VRAM_FRACTION, AGENTIC_MAX_VRAM_GB, AGENTIC_DISABLE_HARDWARE_FILTER, …

configAGENTIC_MAX_VRAM_GBAGENTIC_AVAILABLE_ARCHITECTURES, AGENTIC_ASSUME_GPU, AGENTIC_ASSUME_TPU, AGENTIC_ASSUME_VRAM_GB, AGENTIC_MAX_VRAM_FRACTION, AGENTIC_MAX_VRAM_GB, AGENTIC_DISABLE_HARDWARE_FILTER, …

configAGENTIC_DISABLE_HARDWARE_FILTERAGENTIC_AVAILABLE_ARCHITECTURES, AGENTIC_ASSUME_GPU, AGENTIC_ASSUME_TPU, AGENTIC_ASSUME_VRAM_GB, AGENTIC_MAX_VRAM_FRACTION, AGENTIC_MAX_VRAM_GB, AGENTIC_DISABLE_HARDWARE_FILTER, …

configAGENTIC_RESIDENT_HEADROOM_GB

configAGENTIC_MAX_RESIDENT_MODELS

configAGENTIC_EXEC_QUEUE_EXEC_CPU_CORES

configAGENTIC_ASSUME_VRAM_GBAGENTIC_AVAILABLE_ARCHITECTURES, AGENTIC_ASSUME_GPU, AGENTIC_ASSUME_TPU, AGENTIC_ASSUME_VRAM_GB, AGENTIC_MAX_VRAM_FRACTION, AGENTIC_MAX_VRAM_GB, AGENTIC_DISABLE_HARDWARE_FILTER, …

configAGENTIC_KB_DOC_CHARS

configAGENTIC_KB_SNIPPET_CHARS

configAGENTIC_KB_MAX_HITSAGENTIC_LEARNING, AGENTIC_LEARNING_EVAL, AGENTIC_EVAL_MODEL, AGENTIC_KB, AGENTIC_KB_MAX_HITS, …

configAGENTIC_REPLY_LOCALE

configAGENTIC_HARNESS_FEED_PLANNER

configAGENTIC_USER_HARNESS_FEED_PLANNER

configAGENTIC_LEARNINGAGENTIC_LEARNING, AGENTIC_LEARNING_EVAL, AGENTIC_EVAL_MODEL, AGENTIC_KB, AGENTIC_KB_MAX_HITS, …

configAGENTIC_DETECTION_ORT_PROVIDERS

configAGENTIC_OLLAMA_KEEPALIVE_MODEL

configAGENTIC_OLLAMA_KEEPALIVE_MODELS

configAGENTIC_OLLAMA_RESOURCE_SHARING

configAGENTIC_OLLAMA_UPSTREAM

configAGENTIC_OLLAMA_DAEMON_BASE

configAGENTIC_OLLAMA_QUEUE_WAIT_SECONDS

configAGENTIC_OLLAMA_QUEUE_MAX

configAGENTIC_OLLAMA_BROKER_HOST

configAGENTIC_OLLAMA_BROKER_PORT

configAGENTIC_JETSON_OLLAMA_IMAGE

configAGENTIC_JETSON_OLLAMA_MODELS_DIR

configAGENTIC_JETSON_OLLAMA_CONTAINER_NAME

configAGENTIC_ORCHESTRATOR_MAX_PLANNER_TURNSAGENTIC_ORCHESTRATOR_SESSION, AGENTIC_ORCHESTRATOR_DEFAULT_SESSION, AGENTIC_ORCHESTRATOR_MAX_PLANNER_TURNS, AGENTIC_ORCHESTRATOR_EXCERPT_CHARS, …

configAGENTIC_REACH_PROMPT_CHARS

configAGENTIC_PLANNER_STRICT_PROVIDER_IDS

configAGENTIC_GENERAL_PURPOSE_AGENT_IDS

configAGENTIC_PLANNER_REMAP_ANY_UNKNOWN_ID

configAGENTIC_DISABLE_DOMAIN_PROVIDER_SUPPRESSION

configAGENTIC_DOMAIN_PROVIDER_MATCH_MIN

configAGENTIC_RAG_EMBED_BATCH

configAGENTIC_RAG_INJECT_MAX_TOKENS

configAGENTIC_RAG_EMBED_MAX_DOCS

configAGENTIC_REACH_VISION_TIMEOUT_SECONDS

configAGENTIC_REACH_VISION_MODEL

configAGENTIC_K8S_RUN_STORE_MOUNT

configAGENTIC_RUN_STORE_USER_NAMESPACE

configAGENTIC_RUN_STORE_BACKEND

configAGENTIC_PROGRESSAGENTIC_PROGRESS, AGENTIC_STEP_CONTEXT_INJECT, AGENTIC_STEP_CONTEXT_CHARS

configAGENTIC_CREW_MANAGER_MODEL

configWORKFLOW_TOPIC

configAGENTIC_BOOTSTRAP_PYTHON

configAGENTIC_PLANNER_PROVIDER

configAGENTIC_SERVE_SESSION_OVERLAY_TTL_S

configAGENTIC_SERVE_SESSION_OVERLAY_MAX_BYTES

configAGENTIC_SERVE_SESSION_OVERLAY_MAX_ENTRIES

configAGENTIC_SERVE_SESSION_OVERLAY_ENSURE_OLLAMA

configAGENTIC_OLLAMA_OVERLAY_PREWARM

configAGENTIC_OLLAMA_PREWARM_TIMEOUT_SEC

configAGENTIC_STEP_CONTEXT_CHARSAGENTIC_PROGRESS, AGENTIC_STEP_CONTEXT_INJECT, AGENTIC_STEP_CONTEXT_CHARS

configAGENTIC_STEP_CONTEXT_INJECTAGENTIC_PROGRESS, AGENTIC_STEP_CONTEXT_INJECT, AGENTIC_STEP_CONTEXT_CHARS

configAGENTIC_LOG_FORMAT

configAGENTIC_USER_HARNESS_RECORD_STATS

configAGENTIC_VIDEO_FRAME_CACHE

configAGENTIC_VIDEO_VISION_SYNOPSIS

Deployment configuration, supplied by whoever hosts the server. Users are not asked for these.

deployAGENTIC_WEB_SENTRY_DSN

deployPORT

deployAGENTIC_SENTRY_DSN

// quality suggestions

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

29/29 tools missing one or more hints — describe_image_file (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); transcribe_audio_file (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); analyze_video_file (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +26 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Tool test coverage

Only 5/29 tools referenced in tests (17%)

Write tests that reference each tool by name so every tool has at least one test.

No access to sensitive paths

Reads sensitive paths: /.dockerenv

Remove reads of sensitive system paths. If you genuinely need them, document why in the README.

Readable source code

6 files are minified or bundled, which is usually build output rather than concealment

Ship unminified, readable source.

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail

The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.

// improvement guidance — verified publishers only

We have 5 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.

// embed badge in your README

[![M8ven Verified](https://m8ven.ai/badge/mcp/zlatko-lakisic/agentic-orchestration?variant=verified)](https://m8ven.ai/mcp/zlatko-lakisic/agentic-orchestration)

Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.

commit: f9082b5eeecb2f248cf2fa2eff56e2fa40ed30d5

code hash: 01e9de9534204d75762dc7420fc0392d8f1f46478476dfbc72ee0e333c59b60b

view raw JSON →

Check MCPs from inside your assistant

Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check

check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern

How to add it →Free · no account needed · works in any MCP client