Atisbo
Server Details
MCP tools over one Atisbo workspace: Signals, Opportunities, Backlog, Decisions, Living Documents.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 8 tools
The eight tools are conceptually distinct (query, capture, connect, decide, lookup, map, orient, support), but several overlap in practice: atisbo_capture and atisbo_decide both create/update artefacts, docs and knowledge, and atisbo_decide's 'evidence review/grouping' overlaps with atisbo_map's grouping and 'regroup (merge/split)'. Descriptions do supply explicit routing hints (e.g. analyze vs lookup mode=get, anchor vs link_claims), which keeps it workable, but the boundaries require careful reading rather than being self-evident.
Every tool follows the identical atisbo_<verb> pattern with a single, distinct verb (analyze, capture, connect, decide, lookup, map, orient, support). No mixing of casing or verb styles.
Eight tools is a well-scoped surface for a platform covering ingestion, analysis, curation, mapping, orientation and diagnostics. Each tool occupies a genuine functional lane rather than duplicating another, so none feels redundant.
The surface covers the full lifecycle: connect sources, capture signals, analyze/lookup, curate and decide, map/group, orient, and diagnose. Soft-delete is present via connect and decide, but there is no explicit export/bulk-migration or user/permission management operation, leaving minor gaps an agent must work around.
Available Tools
8 toolsatisbo_analyzeAnalyze: aggregates over the corpusARead-onlyInspect
Broad analytical query over claims, solutions, or activity: time filters, grouping, metrics, ready-to-render chart artifact. Use FIRST for analytical questions spanning entities or time windows; a single-entity drill-down is atisbo_lookup mode=get with the entity id.
Inputs: limit, cursor, domain, filters, +5 more. Returns: data, meta
atisbo_captureCapture: record evidence and patchesCDestructiveInspect
Capture Signals or knowledge; update, patch or add evidence to artefacts.
Inputs: mode (required), ops, body, note, +36 more. Returns: result
atisbo_connectConnect: intake source configurationADestructiveInspect
WHERE Atisbo gets its signals. Modes: list, catalog, create (returns endpoint), configure, pause, resume, sync_now, delete (soft-disconnect). THE CATALOG IS NOT THE BOUNDARY: almost anything connects — call catalog and read fallback before saying "Atisbo cannot ingest that". Atisbo only READS a connected system. create returns the signing secret shown ONCE — relay to the human immediately.
Inputs: kind, mode, label, query, +14 more. Returns: result
atisbo_decideDecide: product decisions and delivery closureBDestructiveInspect
CURATE: evidence review/grouping, deal-breakers. EXECUTE: create, update, dispatch or delete Solutions, record Outcomes. DOCUMENT/GOVERN: living docs, coverage, schedules, knowledge, strategy. log_decision is only for external decisions; mutations log themselves. Writes require UUIDs. mode=declare_pm_exception marks a CLAIM as needing a human decision.
Inputs: mode (required), id, note, spec, +88 more. Returns: result
atisbo_lookupLookup: find and open Atisbo entitiesCRead-onlyInspect
Find or open Atisbo entities: snippets, queues, outcomes and implementation context across modes.
Inputs: mode (required), ref, refs, type, +39 more. Returns: result
atisbo_mapMap: product map nodes and edgesBDestructiveInspect
Create/apply maps, generate/edit nodes and edges, anchor claims/snippets, bind metrics, manage claim-snipe maps, regroup (merge/split), build_macros (macros, preview first). Prefer mode=apply for MECE grouping. Anchor and link_claims put a claim on a node differently and both refuse the wrong map kind: anchor sets the TAXONOMY category (auto_node_id); link_claims adds STRUCTURAL-map membership.
Inputs: mode (required), name, note, label, +38 more. Returns: result
atisbo_orientOrient: workspace snapshot and workflow stateARead-onlyInspect
Workspace orientation. Modes: snapshot, whats_new, strategy, integrations. Continue the user's existing workflow; never create a parallel backlog. Living docs cite snippet:// refs — open atisbo_lookup mode=open; corpus via claim depth=work; aggregates via atisbo_analyze; edit via atisbo_lookup mode=doc_patch_context then atisbo_capture mode=patch_artefact (living documents; manual Knowledge documents are edited in place with atisbo_capture mode=update_artefact).
Inputs: mode, task, depth, limit, +2 more. Returns: result
atisbo_supportSupport: diagnose the workspace and MCP itselfARead-onlyInspect
Diagnose Atisbo, including "I connected a source and nothing appeared", "I sent text and no opportunity formed", or "my data is missing". Checks integrations, ingestion, clustering, gates, key scope and migrations, then returns a playbook. share_report files only diagnostics + your text. Use atisbo_lookup/atisbo_analyze for backlog.
Inputs: problem (required), area, share_report, observed_error. Returns: data, meta
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Agile project management over MCP: boards, epics, roadmap, retros, whiteboards, wiki, metrics
Your product team's shared strategic memory — an MCP server your AI tools reason over.
Work management where AI agents are first-class members: tasks, projects, memory over hosted MCP
Workspace where AI agents publish, read and hand off markdown over MCP. No account.
Related MCP Servers
- AlicenseAqualityBmaintenanceLocal-first MCP tools for AI-assisted work receipts, workspace maps, routing ledgers, measured verdicts, and shared state verification across the five Project Telos flagships.5031 npm4Functional Source , Version 1.1, ALv2 Future
- AlicenseNot gradedqualityDmaintenanceAI-native project management with persistent memory for coding agents. 17 MCP tools for features, stories, sprints, architecture decisions, knowledge base, and session tracking.3MIT
- AlicenseNot gradedqualityAmaintenanceSelf-hosted AI workspace exposing semantic document search (RAG via Qdrant and Apache Tika), long-term user memories, and multi-provider AI chat as MCP tools and resources.1,008Apache 2.0
- AlicenseBqualityCmaintenanceShared workspace your AI agents write to. CMMN case management with 184+ MCP tools: cases, tasks, event-driven CMMN workflows with sentries, persistent memory with semantic search, billing and invoicing. OAuth or token auth; cloud-hosted remote MCP endpoint.10034 npmMIT
Glama MCP Gateway
Add one secure layer between your agents and this server.