Skip to main content
Glama
norrietaylor

io.github.norrietaylor/distillery-mcp

Official
by norrietaylor

distillery_store

Capture new knowledge (session notes, bookmarks, meeting minutes) and return an entry ID, detecting near-duplicates and conflicts to maintain data integrity.

Instructions

Store a new knowledge entry and return its ID with dedup/conflict information.

USE WHEN: capturing a new piece of knowledge (session notes, bookmarks, meeting minutes, ideas, etc.) into the Distillery store.

PARAMS:

  • content (str, required): The knowledge content to store.

  • entry_type (str, required): Entry classification. Valid: [session, bookmark, minutes, meeting, reference, idea, inbox, github, person, project, digest, feed].

  • author (str, required): Who authored this entry.

  • project (str, optional): Project scope for the entry.

  • tags (list[str], optional): Tags for categorisation; supports namespaced tags (e.g. "topic/ai").

  • metadata (dict, optional): Arbitrary key-value metadata. Some entry types REQUIRE specific metadata keys (TYPE_METADATA_SCHEMAS); omitting them returns INVALID_PARAMS naming the missing/invalid field:

    • person: expertise (list[str])

    • project: repo (str)

    • digest: period_start, period_end (str)

    • github: repo, ref_type, ref_number; ref_type in [issue, pr, discussion, release]

    • feed: source_url, source_type; source_type in [rss, github] Other types (session, bookmark, minutes, meeting, reference, idea, inbox) accept arbitrary metadata.

  • source (str, optional, default="claude-code"): Origin of the entry. Valid: [claude-code, manual, import, inference, documentation, external].

  • session_id (str, optional): Opaque session identifier for grouping related entries.

  • dedup_threshold (float, optional, default=config): Cosine similarity threshold (0-1) for near-duplicate warnings.

  • dedup_limit (int, optional, default=config): Max duplicates to report.

  • verification (str, optional, default="unverified"): Verification status. Valid: [unverified, testing, verified].

  • expires_at (str, optional): ISO 8601 datetime; entries past expiry appear in stale results.

  • output_mode (str, optional, default="full"): Response verbosity. Valid: [full, summary]. Use "summary" for bulk imports to skip dedup/conflict checks.

  • include_conflict_prompt (bool, optional, default=False): When true, each conflict candidate carries the ~1–2 KB conflict_prompt LLM template required to round-trip through distillery_find_similar(conflict_check=true). Defaults to false to keep store responses small (issue #348).

RETURNS (success): { entry_id: str, persisted: bool, dedup_action: str, conflicts?: list[{entry_id, content_preview, similarity_score, conflict_prompt?}], warnings?: list } RETURNS (error): { error: true, code: "INVALID_PARAMS" | "BUDGET_EXCEEDED" | "INTERNAL", message: "..." }

RELATED: distillery_find_similar (for pre-store dedup checks), distillery_correct (to supersede an existing entry)

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
tagsNo
authorYes
sourceNo
contentYes
projectNo
metadataNo
entry_typeYes
expires_atNo
session_idNo
dedup_limitNo
output_modeNo
verificationNo
dedup_thresholdNo
include_conflict_promptNo
Behavior5/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It covers return formats for both success and error cases, explains dedup behavior, conflict_prompt inclusion (with size and default rationale), metadata requirements per entry type, expiry semantics, and output_mode effects. It also notes the performance tradeoff of include_conflict_prompt. This is exceptionally transparent for a mutation tool.

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

Conciseness5/5

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

Though lengthy, the description is highly structured with clear sections (USE WHEN, PARAMS, RETURNS, RELATED). Every sentence provides necessary information—there is no filler. The purpose is front-loaded, and the parameter documentation is organized and scannable. Given the tool's complexity (14 parameters with conditional logic), the length is justified and the layout enhances usability.

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

Completeness5/5

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

The description covers everything an agent needs to invoke the tool correctly: all required and optional parameters, enum values, defaults, metadata requirements, return structures for both success and error, error codes, and related tools. With no output schema, it fully documents return values. It even includes edge-case details like default conflict_prompt behavior. Nothing essential is missing.

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

Parameters5/5

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

Schema description coverage is 0%, so the description must fully explain every parameter. It does: each parameter is listed with its type, required/optional status, defaults, valid enums, and special conditional requirements (e.g., metadata schemas per entry_type). This adds immense value beyond the raw input schema, which only provides types and defaults without semantics.

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

Purpose5/5

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

The description opens with a precise verb+resource: 'Store a new knowledge entry and return its ID with dedup/conflict information.' It clearly identifies the action and output. The RELATED section names sibling tools (distillery_find_similar, distillery_correct) and states their different purposes, effectively distinguishing this tool from its siblings.

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?

The 'USE WHEN' section explicitly states the intended usage scenarios (capturing new knowledge like session notes, bookmarks, meeting minutes). It also provides guidance on when to use the summary output_mode for bulk imports and names alternatives (distillery_find_similar for pre-store dedup checks, distillery_correct to supersede an entry), giving clear when-to-use vs. when-not-to-use direction.

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/norrietaylor/distillery'

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