mcp-aurekai
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| akai_apiC | AkaiAPI v2 — Async HTTP gateway for the Akai binary family. (category: platform) |
| akai_authC | AkaiAuth — user management and session tokens. (category: platform) |
| akai_briefD | preserve document order */. (category: artifacts) |
| akai_cliC | akai — unified CLI dispatcher. (category: platform) |
| akai_cmsD | AkaiCMS — stripped binary CMS. (category: data) |
| akai_canonC | AkaiCanon — structure-aware canonicalization via Tree-sitter. (category: data) |
| akai_capabilityC | akai-capability - capability discovery and matching layer. (category: platform) |
| akai_clipsD | AkaiClips — Clip Discovery Engine. (category: media) |
| akai_competeC | akai-compete — stage/model A/B competition engine. (category: specialized) |
| akai_compressC | AkaiCompress — family-aware compression engine. (category: data) |
| akai_controlC | akai-control — control plane for Akai inference pipelines. (category: misc) |
| akai_detect_objectsC | AkaiDetectObjects — Object detection operator for V1/I1 pipelines. (category: specialized) |
| akai_discipD | AkaiDiscipl operator. (category: specialized) |
| akai_distributeD | AkaiDistribute operator. (category: artifacts) |
| akai_economyC | akai-economy — cost-aware routing and budget enforcement. (category: specialized) |
| akai_embedC | AkaiEmbed — text embeddings via ONNX Runtime C API. Produces: .bfvec. (category: inference) |
| akai_emitC | AkaiEmit — multi-format output engine. (category: artifacts) |
| akai_entityD | akai-entity — universal identity resolution layer. (category: knowledge) |
| akai_fpqD | main.c — akai-fpq CLI. Produces: .bfq. (category: inference) |
| akai_fpqxC | akai-fpqx — Cross-family FPQ alignment. Accepts: .bfq. Produces: .bfqx. (category: inference) |
| akai_familyC | akai-family - conceptual family browser for Akai. (category: specialized) |
| akai_financeC | AkaiFinance — service arbitrage, labor pipeline, and bundle pricing engine. (category: data) |
| akai_flash_qlaC | akai-flashqla — AkaiGDN Chunked Prefill (native C kernel). (category: inference) |
| akai_flowD | akai-flow — coroutine-native pipeline programming. (category: pipeline) |
| akai_fragmentC | AkaiFragment — Fragment system CLI. (category: knowledge) |
| akai_frame_extractD | akai-frame-extract. (category: media) |
| akai_gateC | AkaiGate — license enforcement + access control. (category: pipeline) |
| akai_genC | akai-gen — natural language → recipe YAML generator. (category: data) |
| akai_graphC | AkaiGraph — Merkle-DAG artifact graph engine. Produces: .bfgraph. (category: knowledge) |
| akai_hashC | AkaiHash — content-addressing + Merkle DAG hashing engine. (category: artifacts) |
| akai_indexC | AkaiIndex — artifact family indexer and search engine. (category: knowledge) |
| akai_ingestC | AkaiIngest — universal intake binary. (category: artifacts) |
| akai_kv_cacheD | akai-kvcache — v8 RLF KV cache compression. (category: knowledge) |
| akai_layerC | akai-layer — Layer-aware ONNX model inspection and extraction (C port). (category: knowledge) |
| akai_leapfrogB | akai-leapfrog — Hamiltonian conservation and reversibility test. Accepts: .bfq, .bfvec. (category: inference) |
| akai_learnC | akai-learn — artifact-level feedback and threshold tuning. (category: inference) |
| akai_ledgerD | AkaiLedger — value accounting engine. (category: artifacts) |
| akai_mfa_dictD | AkaiMFADict operator. (category: specialized) |
| akai_media_prepD | AkaiMediaPrep operator. (category: media) |
| akai_meterC | AkaiMeter — usage metering + billing events. (category: platform) |
| akai_moqC | akai-moq — Media over QUIC style relay for Akai. (category: specialized) |
| akai_modelC | AkaiModel — model dependency manager for akai pipelines. Produces: .bfmodel. (category: inference) |
| akai_narrateC | AkaiNarrate v3 — Verified Tone-Aware Text-to-Speech Synthesis. (category: media) |
| akai_netD | akai-net — Akai Netlist Runtime. (category: platform) |
| akai_offerD | Also try to read proof-summary.json from. (category: artifacts) |
| akai_orchestrateD | AkaiOrchestrate operator. (category: pipeline) |
| akai_outreachD | AkaiOutreach — quiet distribution engine. (category: data) |
| akai_packC | AkaiPack operator. Produces: .bf, .bfa. (category: artifacts) |
| akai_paragraphD | AkaiParagraph operator. (category: knowledge) |
| akai_payC | AkaiPay — payment & invoice management. (category: data) |
| akai_physicsC | akai-physics — Hamiltonian Version Control Protocol (HVCP) CLI. (category: inference) |
| akai_pipelineC | AkaiPipeline — unified single-process pipeline. (category: pipeline) |
| akai_projectC | AkaiProject operator. (category: data) |
| akai_proofC | AkaiProof operator. Accepts: .bf. Produces: .bfproof. (category: artifacts) |
| akai_proxyC | AkaiProxy — OpenAI-compatible API shim for Akai binaries. (category: platform) |
| akai_quantC | akai-quant — FPQ v8 Recursive Lattice-Flow weight quantization. (category: data) |
| akai_queryC | AkaiQuery — local analytics engine over artifacts via DuckDB. (category: knowledge) |
| akai_queueC | AkaiQueue v2 — SQLite-backed job queue with built-in worker daemon. (category: pipeline) |
| akai_reasonD | akai-reason — Reason-state operator over the HVCP stack. (category: specialized) |
| akai_recipeC | AkaiRecipe — Recipe Registry Management. Produces: .bfrecipe. (category: pipeline) |
| akai_renderD | AkaiRender operator. (category: artifacts) |
| akai_repurposeC | AkaiRepurpose — Transform brief artifacts into social media formats. (category: media) |
| akai_runC | AkaiRun — Recipe Executor. (category: pipeline) |
| akai_runtimeD | Try top-level sibling path: ../SiblingDir/binary */. (category: platform) |
| akai_saeC | akai-sae — SAE feature dictionary runtime. Produces: .bfsae. (category: inference) |
| akai_sliC | akai-sli — Structured Layer Inference. Accepts: .bfqx, .bfsae. (category: inference) |
| akai_scene_detectD | akai-scene-detect. (category: media) |
| akai_segmentC | AkaiSegment — Idea Boundary Detection + Segment Graph. (category: specialized) |
| akai_spaceD | akai-space — shared memory substrate. (category: knowledge) |
| akai_speech_loopC | AkaiSpeechLoop — Whisper → Transform → Piper speech transformation. (category: media) |
| akai_stitchC | AkaiStitch — DAG materializer. (category: media) |
| akai_surfaceD | AkaiSurface operator. (category: specialized) |
| akai_swarmC | AkaiSwarm — P2P artifact distribution via BitTorrent v2 protocol. (category: pipeline) |
| akai_syncD | AkaiSync operator. (category: artifacts) |
| akai_tagC | AkaiTag — instant intent/topic tagging via fastText (pure C). Produces: .bftag. (category: knowledge) |
| akai_telC | AkaiTel — FreeSWITCH Event Socket telephony adapter. (category: platform) |
| akai_tierC | akai-tier — latency tier management and SLA enforcement. (category: data) |
| akai_timeC | akai-time — temporal pipeline manager. (category: data) |
| akai_toneC | AkaiTone — speech tone/emotion/rhythm extraction via OpenSMILE. Produces: .bftone. (category: media) |
| akai_transcribeD | ================================================================. (category: media) |
| akai_transcript_cleanD | AkaiTranscriptClean operator. (category: specialized) |
| akai_transcript_familyD | AkaiTranscriptFamily operator. (category: specialized) |
| akai_vecC | AkaiVec — local vector search via sqlite-vec. Accepts: .bf. Produces: .bfvec. (category: knowledge) |
| akai_video_demuxD | akai-video-demux. (category: media) |
| akai_violenceD | akai-violence — real coupling test harness. (category: specialized) |
| akai_watchD | AkaiWatch operator. (category: platform) |
| akai_weaviate_indexD | AkaiWeaviateIndex operator. (category: specialized) |
| akai_wireC | AkaiWire operator. (category: platform) |
| akai_workflowC | akai-workflow - workflow profile browser. (category: pipeline) |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 89 tools
With 89 tools, many have overlapping purposes despite broad categories. Tools like akai_fpq, akai_fpqx, akai_quant, and akai_flash_qla all relate to quantization/inference, while many 'operator' tools (e.g., akai_discip, akai_fragment) have vague descriptions making them hard to distinguish. The brief and jargon-heavy descriptions further hinder clear differentiation.
All tools share the 'akai_' prefix and use snake_case, but the second part varies between single words (akai_cli, akai_gen) and multi-word phrases (akai_detect_objects, akai_frame_extract). Some are verbs (akai_compress), others nouns (akai_model), showing no consistent verb_noun pattern. This inconsistency makes the set moderately predictable.
89 tools is far above the typical well-scoped range. While the server covers a broad domain (AI/ML pipelines), the sheer number overwhelms an agent's ability to efficiently select the right tool. Many tools appear to be low-level or specialized, suggesting the surface could be consolidated.
Given the large number of tools, the server likely covers many aspects of its domain, but the vague descriptions make it difficult to assess whether CRUD or lifecycle operations are complete. There appear to be many specialized inference and pipeline tools, but gaps in common operations like error handling or logging are apparent.