Mneme Decision MCP

Official

by MnemeHQ

Overview Schema Source Related Servers Discussions Admin

Python

Local

Propose a decision (non-authoritative)

decision.propose

Idempotent

Submit an architectural decision candidate as a non-authoritative proposal. It enters the index for review; only human approval can make it canonical.

Instructions

Submit one candidate architectural decision. The proposal enters the Mneme decision index as a non-authoritative proposal with status 'proposed'. This grants NO authority: the proposal is never enforceable and can only become canonical through separate Mneme human authority (D2C), which this MCP does not expose. Repeated identical source/version/content submissions are idempotent. Use decision.propose_batch when submitting multiple candidates.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`candidate`	Yes	One candidate with a non-empty title and statement plus source provenance; authoritative fields are rejected.

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed15 schema fields changedv0.9.2Sep 22, 2026
- addedInput schema / $defs / CandidateInput / properties / architecture_context / description
```
Added value: +"Optional string key/value context captured with the proposal."
```
- addedInput schema / $defs / CandidateInput / properties / provenance / description
```
Added value: +"Source provenance for this candidate. Required by decision.propose; in decision.propose_batch it may be omitted when shared_provenance is supplied."
```
- addedInput schema / $defs / CandidateInput / properties / rationale / description
```
Added value: +"Optional explanation of why the decision is being proposed."
```
- addedInput schema / $defs / CandidateInput / properties / related_decision_ids / description
```
Added value: +"Optional stable ids of related proposals or canonical decisions."
```
- addedInput schema / $defs / CandidateInput / properties / scope_hints / description
```
Added value: +"Optional opaque retrieval hints for contexts or paths; these are not typed-rule applicability selectors."
```
- addedInput schema / $defs / CandidateInput / properties / statement / description
```
Added value: +"Non-empty statement of the architectural decision being proposed."
```
- addedInput schema / $defs / CandidateInput / properties / title / description
```
Added value: +"Non-empty concise title for the candidate decision."
```
- addedInput schema / $defs / SourceProvenanceInput / properties / external_source_id / description
```
Added value: +"Optional stable identifier assigned by the source system."
```
- addedInput schema / $defs / SourceProvenanceInput / properties / origin_classification / description
```
Added value: +"Declared origin of the proposed content."
```
- addedInput schema / $defs / SourceProvenanceInput / properties / producer_name / description
```
Added value: +"Name of the agent, integration, or system proposing the decision."
```
- addedInput schema / $defs / SourceProvenanceInput / properties / producer_type / description
```
Added value: +"Type of producer, such as agent, integration, or import."
```
- addedInput schema / $defs / SourceProvenanceInput / properties / repository_locator / description
```
Added value: +"Optional repository path or locator associated with the source."
```
- addedInput schema / $defs / SourceProvenanceInput / properties / source_reference / description
```
Added value: +"Human-readable reference to the source output or artifact."
```
- addedInput schema / $defs / SourceProvenanceInput / properties / source_version / description
```
Added value: +"Optional source revision or version used for idempotent identity."
```
- addedInput schema / properties / candidate / description
```
Added value: +"One candidate with a non-empty title and statement plus source provenance; authoritative fields are rejected."
```
First observedv0.9.1Sep 21, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations already include idempotentHint=true and destructiveHint=false, but the description adds substantial non-obvious behavior: the proposal is non-authoritative, has status 'proposed', is never enforceable, and exists only in the index until separate Mneme human authority (D2C) acts. It also reiterates idempotency in a concrete way tied to source/version/content, going beyond the bare annotation.

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

Conciseness4/5

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

The description is front-loaded with the core action and then delivers key caveats in order. It is slightly repetitive ('non-authoritative proposal' vs. 'grants NO authority... never enforceable'), but every sentence earns its place and flows logically.

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?

For a single-parameter tool with complete schema coverage, an output schema, and annotations covering idempotency and non-destructiveness, the description fills the main gaps: authority semantics, status effect, and the batch alternative. Nothing an agent needs to select and invoke it correctly is missing.

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%, and the nested schema already documents provenance, idempotent identity via source_version, and field constraints. The tool description adds no parameter-specific detail beyond restating that a single candidate is submitted; the idempotency note is already reflected in the schema. Baseline 3 applies.

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 states a specific verb ('Submit') and resource ('one candidate architectural decision') and immediately distinguishes itself from the sibling by noting the proposal enters the index as a non-authoritative proposal. It names the batch alternative later, making it easy to tell apart from propose_batch even before reading schemas.

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 description explicitly directs the agent to 'Use decision.propose_batch when submitting multiple candidates,' which is a clear when-to-use vs. alternative condition. It also explains what this tool does NOT do (never enforceable, cannot become canonical via this MCP), preventing off-label use for authoritative decisions.

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

Deploy Server