Memory Journal MCP Server

Create Entry

create_entry

Creates a structured markdown journal entry with type, tags, and impact/trust/validation scores to preserve project context and enable session handoff.

Instructions

Create a new journal entry. Content must be well-structured markdown using ## section headers. Select the most accurate entry_type (e.g., retrospective, personal_reflection, technical_note). For session summaries, use entry_type "retrospective" with tag "session-summary" and structure content as: ## Accomplished, ## Unfinished / Blocked, ## Context for Next Session. REQUIRED: You MUST include project_number. Extract this by querying memory://agent-id. REQUIRED: You MUST include impact_score, trust_score, and validation_status. REQUIRED: You MUST use related_to to anchor the entry to a session summary or nearby context.

Input Schema

Name	Required	Description	Default
`tags`	No	Tags for categorization (kebab-case). Session summaries MUST include "session-summary". DO NOT hallucinate fake tags. Only use tags that genuinely match the content or existing repository vocabulary, domain tags (e.g., "security", "performance") and activity tags (e.g., "refactor", "audit"). [ANTI-HALLUCINATION] MUST be an array of strings, e.g. ["tag1", "tag2"]. NEVER pass a single string.
`pr_url`	No
`anchors`	No	Files or lines of code that this entry is fundamentally anchored to. If the anchor becomes stale/invalid, the entry importance score drops.
`content`	No	Markdown-formatted entry content. Use ## section headers to organize content. Note: The primary text is stored in the `content` property (not `entry`, `title`, `message`, `name`, `description`, or `text`). For session summaries (entry_type: "retrospective", tagged "session-summary"), MUST use EXACTLY: ## Accomplished, ## Unfinished / Blocked, ## Context for Next Session, ## Commits. Do NOT invent extra top-level sections for session summaries.
`issue_url`	No
`pr_number`	No
`pr_status`	No
`entry_type`	No	Entry type. Use "retrospective" for session summaries, "bug_fix" for bugs, "feature_implementation" for features, "planning" for roadmaps, "technical_note" for implementation notes. Do NOT default to "personal_reflection" unless the entry is genuinely a personal note.	personal_reflection
`session_id`	No	Agent session ID for thread isolation (usually conversation ID).
`is_personal`	No
`trust_score`	No	Heuristic score (0.0-1.0) indicating confidence (0.3-0.5 for unverified, 0.9+ for verified).
`auto_context`	No	JSON string with structured metadata. Used for session-commits context.
`impact_score`	No	Heuristic score (0.0-1.0) indicating blast radius (0.9+ for core architecture, 0.1 for simple docs).
`issue_number`	No
`workspace_id`	Yes	REQUIRED. The repository name (e.g. adamic). Do not use numeric project IDs or "workspace" as the key.
`project_owner`	No
`relationships`	No	Optional array of links to previous entries/flags to establish relationships immediately upon creation. Types: "resolves", "depends_on", "implements", "relates_to", "references", "evolves_from"
`workflow_name`	No
`project_number`	No	Numeric project ID (e.g., 1, 14). This is now optional; workspace_id is preferred.
`share_with_team`	No	If true, saves a copy of this entry to the Team database (if configured) using your team alias
`workflow_run_id`	No
`workflow_status`	No
`significance_type`	No
`validation_status`	No	Current validation status of the entry (passed, none, failed).

Output Schema

Name	Required	Description
`id`	No
`code`	No	Error code (e.g. VALIDATION_ERROR, INTERNAL_ERROR)
`entry`	No
`error`	No	Human-readable error message
`author`	No
`details`	No	Additional error context
`success`	No
`category`	No	Error category (validation, query, connection, internal)
`suggestion`	No	Suggested fix for the error
`recoverable`	No	Whether the error is recoverable
`sharedWithTeam`	No
`aggregated_errors`	No	Details of individual errors in a multi-step operation

Schema Changelog

Changes observed during successful MCP inspections.

First observedv9.0.0Nov 2, 2026

TDQS

B3.3/5.0

Behavior3/5

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

Annotations already declare the write/non-destructive/non-idempotent profile, and the description usefully adds preconditions (mandatory fields, a memory://agent-id lookup to resolve project_number). However, it asserts project_number is "REQUIRED" while the schema explicitly says it is now optional and workspace_id is preferred, so the behavioral contract is internally inconsistent.

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?

Front-loads purpose and the session-summary recipe, which is good, but the triple "REQUIRED: You MUST include..." phrasing is repetitive and several rules (markdown ## headers, session-summary tag) duplicate what the schema descriptions already state verbatim.

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

Completeness3/5

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

An output schema exists so return values need no explanation, and the description covers content format and the main semantic fields. The unresolved conflicts (project_number required vs optional, related_to vs relationships) and the absence of any guidance on the many secondary fields leave an agent guessing at call time.

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

Parameters2/5

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

Schema coverage is only 54% across 24 parameters, so the description should compensate, and it does add real meaning for content structure, entry_type selection, and the score fields. But it instructs the agent to "use related_to" — a parameter that does not exist in the schema (the field is relationships[].targetId/relationType), which is actively misleading, and it leaves the other undocumented params untouched.

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?

Opens with a specific verb and resource ("Create a new journal entry") and immediately scopes what counts as valid content. It never distinguishes itself from siblings like batch_create_entries or team_create_entry, which an agent must infer from name alone.

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

Usage Guidelines4/5

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

Gives real selection guidance for entry_type ("use 'retrospective' for session summaries", "do NOT default to personal_reflection") and a concrete recipe for the session-summary case. It offers no when-not guidance and no routing versus team_create_entry or batch_create_entries.

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

Deploy Server