Skip to main content
Glama
contextstream

ContextStream MCP Server

Memory

memory
Read-onlyIdempotent

Create, read, update, delete, search, and organize events, nodes, tasks, todos, diagrams, documents, transcripts, and team items with specialized operations.

Instructions

Memory operations for events and nodes. Event actions: create_event, get_event, update_event, delete_event, list_events, distill_event, import_batch (bulk import array of events). Node actions: create_node, get_node, update_node, delete_node, list_nodes, supersede_node. Query actions: search, decisions, timeline, summary. Task actions: create_task (create task, optionally linked to plan), get_task, update_task (can link/unlink task to plan via plan_id), delete_task, list_tasks, reorder_tasks. Todo actions: create_todo, list_todos, get_todo, update_todo, delete_todo, complete_todo. Diagram actions: create_diagram, list_diagrams, get_diagram, update_diagram, delete_diagram. Doc actions: create_doc, list_docs, get_doc, update_doc, delete_doc, create_roadmap. Transcript actions: list_transcripts (list saved conversations), get_transcript (get full transcript by ID), search_transcripts (semantic search across conversations), search_archive (remote Atlas archive; local npm returns unavailable), delete_transcript. Team actions (team plans only): team_tasks, team_todos, team_diagrams, team_docs.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
actionYesAction to perform
workspace_idNoWorkspace ID (UUID).
project_idNoProject ID (UUID).
event_idNoEvent ID (UUID).
node_idNoNode ID (UUID).
titleNoShort descriptive title.
contentNoFull content/body.
event_typeNoInput parameter: event type.
node_typeNoInput parameter: node type.
metadataNoInput parameter: metadata.
queryNoSearch query string.
scopeNoArchive collection scope for search_archive: transcripts, decisions, lessons, docs
categoryNoInput parameter: category.
limitNoMaximum number of results to return.
agentNoAgent identity metadata (capture/create filters) and query filter. Matches both structured `agent` and `agent:<name>` tag fallback.
modeNoMode metadata (capture/create filters) and query filter. Matches both structured `mode` and `mode:<value>` tag fallback.
relationsNoInput parameter: relations.
new_contentNoFor supersede_node: the new content to replace the node with
reasonNoFor supersede_node: reason for the supersede
provenanceNoInput parameter: provenance.
code_refsNoInput parameter: code refs.
task_idNoTask ID for get_task/update_task/delete_task (full 36-char UUID)
plan_idNoPlan ID (full 36-char UUID): for create_task (link to plan), update_task (set UUID to link, null to unlink), list_tasks (filter by plan)
plan_step_idNoWhich plan step this task implements
descriptionNoDescription for task
task_statusNoTask status
statusNoBackward-compatible alias for task_status in task actions
priorityNoTask priority
orderNoTask order within plan
task_idsNoTask IDs for reorder_tasks
blocked_reasonNoReason when task is blocked
tagsNoTags for event or task categorization
eventsNoArray of events for import_batch action
todo_idNoTodo ID for get_todo/update_todo/delete_todo (full 36-char UUID)
todo_priorityNoTodo priority
todo_statusNoTodo status filter for list_todos, or status update value for update_todo
completedNoTodo completion flag for update_todo
due_atNoDue date (ISO 8601) for todo
diagram_idNoDiagram ID for get_diagram/update_diagram/delete_diagram (full 36-char UUID)
diagram_typeNoMermaid diagram type
doc_idNoDoc ID for get_doc/update_doc/delete_doc. For get_doc, accepts UUID or title/query text.
doc_typeNoDocument type
milestonesNoMilestones for create_roadmap action
is_personalNoMark as personal (only visible to creator). For create/list actions on todos, diagrams, docs.
transcript_idNoTranscript ID for get_transcript/delete_transcript (full 36-char UUID)
session_idNoSession ID filter for list_transcripts
client_nameNoClient name filter for list_transcripts (e.g., 'claude', 'cursor')
started_afterNoISO timestamp - filter transcripts started after this time
started_beforeNoISO timestamp - filter transcripts started before this time
Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare readOnlyHint=true and idempotentHint=true, but the description includes destructive actions like delete, supersede, and update, which contradicts the readOnly annotation. This is a clear Annotation Contradiction, and the description fails to address behavioral traits like authorization needs or side effects.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is excessively long (over 30 lines) and repetitive, listing every action without prioritization. It lacks front-loading of key information and efficient structure.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite the tool's high complexity (49 parameters, nested objects), the description fails to explain return values, provide examples, or clarify behavior for specific actions. It is incomplete as a standalone guide.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description adds minimal semantic value beyond the schema, mostly repeating parameter names and types. It does not compensate for missing schema details.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states 'Memory operations for events and nodes' and enumerates many sub-actions, making it clear that the tool handles various memory-related CRUD and query operations. However, given sibling tools like 'mem' and 'entity', the description does not differentiate this tool from them.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. It simply lists actions without explaining context, prerequisites, or exclusions, leaving the agent to infer usage.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/contextstream/mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server