Stele
Server Details
Shared project memory for AI coding agents: decisions, lessons, risks and tasks in one graph.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- OAuth
- Works in Glama
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- Stele-Dev/stele-mcp-connector
- GitHub Stars
- 0
- ChatGPT
- Stele
- Claude
- –
TDQS
Scored across 20 tools
The read tools (fetch, inspect, recall, search, show_node) are unusually well-differentiated through explicit cross-references in their descriptions. However, `list` with what="nodes" overlaps the dedicated `list_tasks`, fetch vs show_node is a subtle self-vs-user split, and consequential operations are scattered into a catch-all `destructive` tool, so an agent must remember that cancel_task/force_claim_task/unlink/retire_objective live there rather than in the matching resource tool.
Resource-noun tools with an `action` parameter (task, knowledge, node, objective, workspace, comment, timeline, organize, project) coexist with bare-verb tools (fetch, recall, search, inspect, list) and UI openers (open_stele, open_project_board); each group is internally consistent but the set mixes conventions. The `destructive` tool is named by risk rather than domain, which breaks the otherwise readable resource-oriented scheme.
Twenty tools is defensible given the breadth of the domain — tasks, knowledge, documents, diagrams, objectives, workspaces, components, topics, comments, timeline, search/recall, and two UI openers. Still, it sits in heavy territory, and folding the `destructive` actions back into their owning resource tools would materially trim the surface.
Lifecycle coverage is strong: tasks have claim/complete/release/reopen/force_release, knowledge has create/review/dedupe, objectives run from create through achieve and retire, and comments, timeline, workspaces and read/recall paths are all covered. Minor gaps remain — there is no clear node or project deletion path, and several operations (run_loop_attempt, loop, workspace activation) fail closed or are unavailable on hosted connections.
Publisher details
- Operator
- Stele AI LLC · Publisher source
- Operator website
- https://stele-ai.dev
- Vendor relationship
- First-party
- Documentation
- https://stele-ai.dev/docs
- Trust center
- https://stele-ai.dev/security
- Restrictions
- free for OSS and personal use. Pro plan available. · Publisher source
Available Tools
20 toolscommentComment on a nodeADestructiveInspect
Discuss on a node. action = add | update | resolve (mark a thread settled) | delete (soft tombstone; replies are preserved). Replies are one level deep: reply to a top-level comment only. Read a node's comments with list(what="comments").
Returns: data, action
destructiveConsequential actionsADestructiveInspect
Operations that require extra caution or confirmation. dedupe_knowledge is a read-only candidate scan; the remaining actions are consequential. Action names carry their resource because this tool spans resources. action = cancel_task | force_claim_task | dedupe_knowledge | dedupe_pair | unlink | restore_node_version | retire_objective | merge_workspace | cherry_pick_workspace | archive_workspace | archive_component | merge_topics | run_loop_attempt | doctor. run_loop_attempt executes the exact declared shell command supplied in the approval arguments with a scrubbed environment when trusted local repository execution is available; hosted MCP fails closed.
Returns: data, action
documentCreate documents and diagramsAInspect
Create long-form artifacts. action = create (a document — a plan, spec, or imported file) | create_diagram (a d2 diagram node). For create, pass the body inline or a repo-relative file_path for the server to read. file_path works only on a local connection; over a hosted connection pass the body inline. Recall and search surface a document by title only; read its body with fetch.
Returns: data, action
fetchFetch a node in fullARead-onlyInspect
Fetch one node in full by its shareable id (TASK-N/KNOW-N/COMP-N/DOC-N/DIAG-N/EPIC-N/NODE-N), with its edges — this is how you read a full body (recall/search return summaries). Pass version to fetch a historical snapshot instead of the current one.
Inputs: id (required), project_slug (required), version. Returns: data, action
inspectInspect a node in depthARead-onlyInspect
Look at what surrounds one node or the whole project: its connections, its history, and the project's state. Read-only. Use fetch for a node's own content, search to find nodes by their words, and recall to gather context for a question; use inspect when you need more than the node itself. Actions: context: a scored neighborhood of decisions, risks and tasks connected to a node, query or topic; read it before changing something it touches. provenance: the cited chain of why a node exists and what it superseded; check it before relying on or overriding a decision. briefing: the project's working rules, root components and suggested first calls; call it once at the start of a session. claim_history: who claimed and released a task, and when; check it before force-claiming a task that looks abandoned. workspace: one workspace overlay's details. stats: project totals, overdue commitments, likely-abandoned tasks and recent activity, in one call. loop: verify a task's protected check paths against local Git state; local only, and it fails closed. rag_status: what automatic topic recall is focused on now; local only.
Returns: data, action
knowledgeCapture knowledgeAInspect
Capture or curate knowledge. action = create (file a typed fact — decision, lesson, risk, …) | review (mark a node re-verified against current reality). create files one fact under a component; it requires a lifecycle choice (expires_on_task, expires_at, due_at — pass null to skip each), and durable decisions and architecture usually skip all three. Merging duplicate knowledge lives in the destructive tool.
Returns: data, action
listList a collectionARead-onlyInspect
List a collection: what = nodes | components | topics | documents | diagrams | objectives | workspaces | comments | node_versions | projects, with per-what filters. what:"projects" is the project-less bootstrap (discover your slugs). Most collections page with limit/offset; a few return everything up to limit with no further paging.
Returns: data, action
list_tasksList tasksARead-onlyInspect
List tasks, most-recently-updated first, filterable by status, component, assignee, and kind — the roadmap/board view of work. It returns task cards without bodies unless include_body is true; read one task in full with fetch. In clients that display apps, the result also renders as a task board for the user, so summarize it rather than repeating every task.
Inputs: project_slug (required), kind, limit, offset, +5 more. Returns: data, action
nodeEdit a nodeADestructiveInspect
Edit a node or its structure. action = update (edit fields/body) | move (re-file under a component or workspace) | link (add a typed edge between two nodes). Removing an edge (unlink) lives in the destructive tool.
Returns: data, action
objectiveShape the roadmapADestructiveInspect
Shape the roadmap. action = create | add_milestone | attach (task → milestone) | move (task → objective) | detach | reorder | set_target | achieve. Retiring an objective lives in the destructive tool.
Returns: data, action
open_project_boardProject boardARead-onlyInspect
Open the Stele project board beside this conversation, so the user can watch tasks while you work on them.
Inputs: project_slug.
open_steleSteleARead-onlyInspect
Open the Stele app for the user: browse their projects, open tasks, recent activity, and search. Use it when the user wants to see or browse their project, not to answer a question.
Inputs: project_slug.
organizeProject housekeepingADestructiveInspect
Housekeeping: change how the project is organized. It never edits a node's content; use node, knowledge or task for that. Actions: add_component: create a durable area of ownership that knowledge and tasks attach to; list the existing components first to avoid a duplicate. rename_topic: rename a topic tag on every node that carries it, for typos and casing. feedback: report how well the memory helped this conversation: a 0–10 score, one strength, one hindrance, one improvement. pause_rag: kept for older clients; automatic topic recall runs only where the memory runs locally, so here it reports that recall is unavailable and changes nothing. Call recall with your question whenever you need context from the graph.
Returns: data, action
projectCreate a projectAInspect
Manage projects. action = create (bootstrap a new project and its root component, owned by you). This is the first thing to call when you have no project yet; discover existing ones with list what:"projects". New projects are private unless you pass visibility:"public"; plans allow a limited number of private projects and unlimited public ones.
Inputs: name (required), action (required), repo_url, visibility, +1 more. Returns: data, action
recallRecall project contextARead-onlyInspect
One-call semantic + full-text recall over the graph — a ranked bundle of the decisions, tasks, risks, and documents most relevant to a question or topic. The default way to load context before acting; reach for search only for an exact-term or document-scoped lookup.
Inputs: question (required), project_slug (required), depth, seed_limit, +2 more. Returns: data, action
searchSearch nodes and documentsARead-onlyInspect
Find nodes or documents by the words they contain. Nothing here matches by meaning, so use recall for a natural-language question. method "keyword" (default): ranked full-text search over active nodes; terms are AND-combined, and a multi-word query that matches nothing is retried once as an OR of its words. It returns cards, not bodies (default limit 5). method "exact": the matching line per node for a literal substring, or a POSIX regex with regex:true, across every status including done and archived (default limit 50). scope "documents": a line search of document bodies, a literal substring or, with regex:true, a JavaScript regex; it ignores method and type, and limit caps the number of documents unless max_docs is set. Every hit carries id, title, and url; limit is at most 50, with no paging. Read a full body with fetch.
Inputs: query (required), project_slug (required), type, limit, +8 more. Returns: data, action
show_nodeShow in SteleARead-onlyInspect
Show one Stele node (a task, knowledge entry, or document) to the user as a card in the conversation: its title, status, body, links, and provenance. Use it when the user wants to see a node. To read a node yourself, use fetch.
Inputs: id (required), project_slug (required).
taskTask lifecycleAInspect
Task lifecycle. action = create | claim | complete | release | reopen | force_release | loop_finalize. Claim before you start and complete when done — these route through the atomic claim path that records accountability; never flip a task's status by hand. loop_finalize keeps correctness, independent review, and intent/scope verdicts separate. Cancelling a task and force-claiming one live in the destructive tool.
Returns: data, action
timelineRead and journal the TimelineAInspect
The project's Timeline: automatic events captured on graph writes and task lifecycle actions, plus one-line custom entries. action = list (read it, newest first, keyset-paginated — not offset-based) | log (append a one-line custom entry). A logged entry is a short journal line, never reasoning or decisions — link the graph nodes that hold those instead. Logging can be turned off for a project; when it is, the call still succeeds but writes nothing.
Returns: data, action
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Shared project memory for coding agents: decisions, lessons, guardrails and tasks per repository.
Project memory for coding agents: requirements, decisions, code graph and delivery telemetry.
Shared debugging memory for AI coding agents
Evidence-backed project memory and checkpoints for AI coding agents.
Related MCP Servers
- FlicenseNot gradedqualityBmaintenancePersistent memory for AI coding agents: local-first semantic search, dependency graphs, git history.1-
- AlicenseNot gradedqualityDmaintenanceShared team memory for AI coding agents with Bayesian confidence scoring and temporal decay, enabling persistent storage and retrieval of engineering patterns across sessions.20 npm18MIT
- AlicenseNot gradedqualityAmaintenancePersistent memory for AI coding agents1,665 PyPI226Apache 2.0
- AlicenseAqualityDmaintenancePersistent shared memory for AI coding agents. Stores facts as entity/key/value triples with hybrid semantic search, task checkpoints, and conflict resolution — shared across Claude Code, Codex CLI, and GitHub Copilot.16235 npm5AGPL 3.0
Glama MCP Gateway
Add one secure layer between your agents and this server.