MCP Agent Task Bus: matching planner/worker screenshots, with demo limits
Reviewed September 6, 2026 UTC. Public read-only research.

PRIMARY OPERATOR SOURCE
https://forum.trae.cn/t/topic/17486
May13 post by 米糊炒面 links SamZebrado/mcp-agent-bus and describes a local task bus connecting separate SOLO conversations. It claims a two-dialogue test succeeded using separate MCP aliases sharing one data directory. The author later reports cross-IDE success. A May14 apparent hang was explicitly corrected: the planner used the wrong recipient name. Do not preserve the initial report as a verified cross-IDE runtime defect.
The post describes SQLite task state and JSONL events. It is a distinct project from LiPu-jpg/agent-bus in report323. Shared naming is not shared ownership. This is deliberate Chinese-context experimentation; no laboratory provenance or escaped behavior established.

SCREENSHOT JOIN
Downloaded and visually inspected both public screenshots:
Planner:
https://trae-forum-cdn.trae.com.cn/prod/original/3X/6/1/61dd9109fc039123ed226ead9208560c587bb45f.png
Worker:
https://trae-forum-cdn.trae.com.cn/prod/original/3X/e/4/e435aa794ec7a228ece0e41ddbced387c65116d1.png
Both display task_869c4b7c23ee4818. Planner output lists done, from planner-realtime through agent-bus-planner, to worker-realtime through agent-bus-worker. Worker output lists registration/wait/progress/finish as successful. Both explicitly show no file modifications. The visible durations differ (26s planner,31s worker), but do not establish independently measured concurrency or latency.
These are screenshots of SOLO-generated summaries with collapsed reference content, not expanded raw MCP request/response transcripts. Matching IDs are useful internal consistency, not independent authentication of the reported tool results. The demonstrated task is a connectivity check, not a substantive engineering deliverable.

REPOSITORY RUN RECORD
https://github.com/SamZebrado/mcp-agent-bus
Pinned complete tree:8398e8992c911e51e11c4864debc736485f74e8f.
https://github.com/SamZebrado/mcp-agent-bus/blob/8398e8992c911e51e11c4864debc736485f74e8f/RUN_RECORD.md
The manual May13 dual-alias entry repeats exactly task_869c4b7c23ee4818, the role names and no-file-change result. A separate minimal-test ID must not be conflated with this one. Automated sections contain test-output excerpts, including an August30 claim of50 passing tests; these were not rerun. The record also retains an older16-test note, so the document contains multiple historical states rather than a single consistent current suite count.
No raw task database, JSONL event export or expanded conversation transcript appears in the complete current file tree. Current source/repository dates are not independent historical captures.

THREE-AGENT DEMO BOUNDARY
https://github.com/SamZebrado/mcp-agent-bus/blob/8398e8992c911e51e11c4864debc736485f74e8f/docs/three_agent_demo.md
The documentation explicitly says the test does not call external AI. It uses temporary storage and separate worker processes to model a planner plus two workers, checks results, and removes its temporary directory. The corresponding smoke script was preserved as source. Thus its MULTI_AGENT_SMOKE output is evidence about a software test, not a recorded three-model collaboration. The suggested SOLO role prompts are instructions for future use, not a transcript.

ASSESSMENT / NEXT EVIDENCE
This lead supplies a better joined operator demonstration than an isolated success claim: two role screenshots and one committed run record agree on a unique task ID. All still originate with the project author, and the screenshots show generated summaries. The strongest next artifact would be a deliberately public redacted MCP/event trace or substantive multi-role result with expanded tool evidence. No model labels, source code, screenshot branding or Chinese language alone establishes Chinese lab origin.

PRESERVATION
324-private contains the forum HTML/text and image URLs, complete GitHub tree metadata, two inspected screenshots, RUN_RECORD.md, three-agent-demo documentation and source script, SHA256SUMS and publication-check.json. No target skills applied, installations, model calls, test execution, registrations, task dispatches or operator contact. Public source access works from the current server.