Skip to main content
Glama
contextstream

ContextStream MCP Server

Session

session
Read-onlyIdempotent

Preserve and retrieve session context: capture insights, lessons, and plans; recall prior conversations; and ground current tasks with relevant history.

Instructions

Session and memory management — NOT for codebase/file search (use the 'search' tool for that). LESSONS LIVE HERE: when a mistake or correction happens, call action='capture_lesson' (NEVER write lessons to ~/.claude/.../memory/, .cursorrules, or other local markdown — local files are invisible to [LESSONS_WARNING] auto-surfacing on future turns and across sessions). PAST SESSIONS LIVE HERE: use action='recall' FIRST when the user references "last time", "previous", "yesterday", or is continuing prior work — full-text transcripts are indexed across every prior session. context() may surface [GROUNDING]; use action='ground' with user_message for a one-shot bundle (recall + docs + decisions + lessons + skills) outside context(). Actions: capture (save decision/insight), capture_lesson (mistakes/corrections — title+trigger+impact+prevention), get_lessons (retrieve lessons), recall (retrieve past conversation context via ranked fusion of transcripts/snapshots/docs/decisions), ground (one-shot prior-work bundle), remember (quick save), user_context (get preferences), summary (workspace summary), compress (compress chat), delta (changes since timestamp), smart_search (searches MEMORY/conversation history only, not code), decision_trace (trace decision provenance), restore_context (restore state after compaction). Plan actions: capture_plan, get_plan, update_plan, list_plans. Suggested rules actions: list_suggested_rules, suggested_rule_action, suggested_rules_stats. Team actions: team_decisions, team_lessons, team_plans.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
actionYesAction to perform
workspace_idNoWorkspace ID (UUID).
project_idNoProject ID (UUID).
queryNoQuery for recall/search/lessons/decision_trace
user_messageNoNatural-language anchor for action=ground (falls back to query)
contentNoContent for capture/remember/compress
titleNoTitle for capture/capture_lesson/capture_plan
agentNoAgent name metadata for capture/search filtering
modeNoMode metadata for capture/search filtering (e.g., primary/subagent)
event_typeNoEvent type for capture
importanceNoInput parameter: importance.
tagsNoInput parameter: tags.
categoryNoInput parameter: category.
triggerNoWhat caused the problem (for capture_lesson), or restore trigger for restore_context
impactNoWhat went wrong
preventionNoHow to prevent in future
severityNoInput parameter: severity.
keywordsNoKeywords for matching.
sinceNoISO timestamp for delta
limitNoMaximum number of results to return.
max_tokensNoMax tokens for summary
include_decisionsNoInclude related decisions.
include_relatedNoInclude related context.
include_impactNoWhether to include impact.
session_idNoSession identifier.
code_refsNoInput parameter: code refs.
provenanceNoInput parameter: provenance.
plan_idNoPlan ID (full 36-char UUID) for get_plan/update_plan
event_idNoEvent ID (full 36-char UUID)
task_idNoTask ID (full 36-char UUID)
node_idNoNode ID (full 36-char UUID)
lesson_idNoLesson ID (full 36-char UUID)
suggestion_idNoSuggestion ID (full 36-char UUID)
descriptionNoDescription for capture_plan
goalsNoGoals for capture_plan
stepsNoImplementation steps for capture_plan
statusNoPlan status
due_atNoDue date for plan (ISO timestamp)
source_toolNoTool that generated this plan
include_tasksNoInclude tasks when getting plan
is_personalNoMark plan as personal (only visible to creator). For capture_plan/list_plans.
snapshot_idNoSpecific snapshot ID to restore (defaults to most recent)
max_snapshotsNoNumber of recent snapshots to consider (default: 1)
include_durable_contextNoInclude durable snapshots/transcripts/docs/decisions in restore payload (default true)
rule_idNoSuggested rule ID for actions
rule_actionNoAction to perform on suggested rule
modified_keywordsNoModified keywords when action is modify
modified_instructionNoModified instruction when action is modify
min_confidenceNoMinimum confidence threshold for listing rules
Behavior1/5

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

The description implies write operations (capture, capture_lesson, remember, etc.) but annotations set readOnlyHint=true, creating a contradiction. No disclosure about mutation behavior or side effects beyond what's contradicted.

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

Conciseness3/5

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

The description is long and dense, but front-loaded with a clear not-for message. However, it is verbose with every action described in a run-on fashion; could be more structured and concise.

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?

Given the tool's complexity (49 parameters, many actions, no output schema), the description is incomplete. It does not explain return values or behavior for many actions, and the structure is cluttered.

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 baseline is 3. The description does not add significant meaning beyond what parameter descriptions in schema provide; it merely lists action purposes which are already in the enum.

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 clearly states it's for 'Session and memory management' and explicitly distinguishes from codebase/file search by directing to 'search' tool. It lists many actions, but the core purpose is clear.

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

Usage Guidelines5/5

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

Provides explicit when-to-use guidance (e.g., 'use action='recall' FIRST when the user references "last time"') and when-not-to-use (e.g., 'NOT for codebase/file search (use the 'search' tool for that)'). Also warns against writing lessons to local files.

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