Which integrations are available for this server?

Allows chatting with local Ollama models, with responses WORM-sealed for verifiable integrity.

How do I use SnapKitty MCP Server?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@SnapKitty MCP Server Generate an Ada contract for cross-chain governance" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

SnapKitty MCP Server

Official

by SNAPKITTYWEST

Overview Schema Related Servers Score Discussions

JavaScript

Local

@snapkitty/mcp-server

Sovereign-grade MCP server for SnapKitty Collective.

Exposes SnapKitty's core capabilities as MCP tools — callable from Claude, any MCP client, or directly via npx.

Tools

Tool	What it does
`worm_seal`	Seal any payload into the SHA-256 WORM chain
`worm_read`	Read and verify the WORM chain
`agent_build`	Create a sovereign agent manifest (SENTINEL/ORACLE/BUILDER/ARCHIVIST/BERSERKER)
`ada_contract_generate`	Generate an Ada-syntax governance contract, WORM-sealed
`twin_chat`	Chat with a local Ollama model, response WORM-sealed
`sovereign_inject`	Generate a Mamba SSM injection spec from Lean 4 theorem + Ada contract

Related MCP server: math-logic-mcp

Install

npm install -g @snapkitty/mcp-server

Claude Desktop config

{
  "mcpServers": {
    "snapkitty": {
      "command": "snapkitty-mcp"
    }
  }
}

Claude Code config (.mcp.json)

{
  "mcpServers": {
    "snapkitty": {
      "command": "npx",
      "args": ["@snapkitty/mcp-server"]
    }
  }
}

Requirements

Node.js 20+
Ollama running locally (for twin_chat — optional, other tools work offline)

Architecture

The sovereign_inject tool implements the BOB/METATRON architecture:

Lean 4 theorem  ──┐
                   ├──→  injection_vector (2048-dim)  ──→  SSM state gate
Ada contract    ──┘                                         h(t) = ā·h(t-1) + b̄·x(t) + W·v_inject

Structured symbolic proofs are embedded into SSM hidden state directly — bypassing the context window. The proof gate fires before state advances. Invalid proofs block state transitions.

Sovereign Stack

Built by SnapKitty Collective | collectivekitty.com

Available Tools

6 tools

ada_contract_generateB

Generate an Ada-syntax sovereign governance contract for an agent. Defines permitted capabilities, trust level, and WORM-seals the contract.

ParametersJSON Schema

Name	Required	Description	Default
`purpose`	No	Human-readable purpose statement
`agent_name`	Yes	Agent name
`agent_class`	Yes
`trust_level`	No		HIGH
`capabilities`	No	Permitted capabilities

TDQS

B3.3/5.0

Behavior3/5

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

The description discloses that the tool defines capabilities and trust level and WORM-seals the contract, but without annotations, it fails to provide deeper behavioral details such as side effects, reversibility, or required permissions.

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?

The description is concise, consisting of two front-loaded sentences with no wasted words. It efficiently conveys the core action and key elements.

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?

Given no output schema or annotations, the description provides a basic understanding of the tool's function but lacks context about return values, storage, or relationship to sibling tools, limiting completeness.

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?

The schema covers 60% of parameters with descriptions. The description adds that capabilities and trust level are defined in the contract, but does not explain agent_class or the meaning of enum values in trust_level or agent_class, leaving semantic gaps.

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 the tool generates an Ada-syntax sovereign governance contract for an agent, specifying permitted capabilities, trust level, and WORM-sealing. However, it does not differentiate from sibling tools like worm_seal or sovereign_inject, which could cause confusion.

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?

No guidance is provided on when to use this tool versus alternatives (e.g., worm_seal, sovereign_inject). The description lacks explicit context for appropriate usage scenarios.

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

agent_buildC

Create a sovereign agent manifest with class, capabilities, model binding, and WORM seal. Classes: SENTINEL, ORACLE, BUILDER, ARCHIVIST, BERSERKER.

ParametersJSON Schema

Name	Required	Description	Default
`name`	Yes	Agent name
`model`	No	Ollama model tag (default: nemotron)	nemotron
`agent_class`	Yes	Agent class
`capabilities`	No	List of permitted capabilities

TDQS

C2.9/5.0

Behavior2/5

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

No annotations provided, so the description must disclose behavior. It mentions 'Create' and 'WORM seal' but does not explain side effects (e.g., persistence, overwrite rules), required permissions, rate limits, or whether the operation is reversible. The tool's mutation nature is implied but unsupported with specifics.

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?

Two sentences, no extra words. The first sentence captures purpose, the second lists classes. Efficient and front-loaded.

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?

With no output schema and no annotations, the description fails to explain what the tool returns (the manifest?), how WORM seal is applied, or any post-creation behavior. The mention of WORM seal is defined nowhere in the schema, causing confusion.

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%, meeting the baseline. The description repeats the enum values for agent_class but adds no new meaning beyond the schema. No additional context for capabilities or model.

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 the verb 'Create' and the resource 'sovereign agent manifest', listing key components (class, capabilities, model, WORM seal) and available classes. However, it does not differentiate from sibling tools, such as ada_contract_generate or sovereign_inject, which could create similar manifests.

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?

No explicit guidance on when to use this tool over alternatives, no prerequisites, and no examples. The description lists classes but does not advise on selection criteria or context for use.

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

sovereign_injectC

Generate a Mamba SSM injection specification from a Lean 4 theorem and Ada contract. This is the BOB orchestrator architecture: structured symbolic proofs injected into SSM state, bypassing the context window.

ParametersJSON Schema

Name	Required	Description	Default
`label`	No	Injection label	sovereign-injection
`ada_contract`	Yes	Ada contract text to bind to the injection
`lean4_theorem`	Yes	Lean 4 proof obligation or theorem statement

TDQS

C2.9/5.0

Behavior2/5

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

With no annotations provided, the description must disclose behavior but only offers architectural jargon ('BOB orchestrator', 'bypassing context window') without explaining side effects, resource requirements, or return format.

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 relatively short but the second sentence adds architectural context that may not be essential for invocation, making it slightly less concise and focused.

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 no output schema, no annotations, and three parameters with sparse schema descriptions, the description lacks details on output format, prerequisites, and expected results, hindering correct use.

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 100% but descriptions are minimal; the tool description restates the parameters without adding meaning, examples, or constraints beyond the schema.

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?

Description clearly states the tool generates a Mamba SSM injection specification from a Lean 4 theorem and Ada contract, making the purpose explicit and distinct from siblings.

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?

No guidance on when to use this tool versus alternatives like ada_contract_generate or twin_chat; the description implies usage when an injection specification is needed but does not provide explicit context or exclusions.

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

twin_chatA

Chat with a local Ollama model as a sovereign digital twin. Response is WORM-sealed. Requires Ollama running locally.

ParametersJSON Schema

Name	Required	Description	Default
`model`	No	Ollama model tag (default: nemotron)	nemotron
`prompt`	Yes	Message to send to the twin
`ollama_host`	No	Ollama host URL (default: http://localhost:11434)	http://localhost:11434
`system_prompt`	No	System prompt / twin identity

TDQS

A3.5/5.0

Behavior3/5

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

With no annotations, the description carries full burden. It discloses that responses are WORM-sealed and requires a local Ollama instance. However, it doesn't explain error behavior, latency implications, or whether it modifies state. The information is basic but present.

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?

Two sentences with no unnecessary words. The first sentence states the main action, the second adds key behavioral and prerequisite info. Highly concise.

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?

Given 4 parameters, no annotations, and no output schema, the description covers the core purpose and a key behavioral trait. However, it omits details about response format, error handling, and how it relates to sibling tools like sovereign_inject or worm_seal. It is barely adequate.

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 coverage is 100%, so each parameter already has a description. The description adds context like 'sovereign digital twin' and 'twin identity' but doesn't add significant new semantics beyond the schema. Baseline 3 is appropriate.

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 chatting with a local Ollama model as a sovereign digital twin. The mention of WORM-sealed response distinguishes it from generic chat tools. However, it could more explicitly differentiate from sibling tools like worm_read or worm_seal, which also deal with WORM data.

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

Usage Guidelines3/5

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

The description provides a prerequisite (Ollama running locally) but does not specify when to use this tool versus alternatives like sovereign_inject or worm_read. No when-not or explicit context is given.

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

worm_readB

Read and optionally verify the SnapKitty WORM chain. Returns recent events and chain validity.

ParametersJSON Schema

Name	Required	Description	Default
`last_n`	No	Return last N events (default 10)
`verify`	No	Verify chain integrity (default true)

TDQS

B3.2/5.0

Behavior2/5

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

No annotations provided, so description carries full burden. It indicates a read operation with no destructive effects, but lacks details on authorization, rate limits, or any side effects. The output is described only vaguely ('returns recent events and chain validity').

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?

Single sentence, no unnecessary words. Efficient and front-loaded with the key action.

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

Completeness4/5

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

For a simple read tool with 2 parameters and no output schema, the description covers the primary function. Context about the chain and verification could be expanded, but it's adequate.

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 coverage is 100% with clear descriptions for both parameters. The description adds minimal value beyond reinforcing that verification is optional, which is already in the schema's default.

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 the tool reads the SnapKitty WORM chain with optional verification, and returns events and validity. It distinguishes from siblings like worm_seal (likely write) by specifying 'Read'.

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?

No explicit guidance on when to use this tool versus alternatives. The optional verification is mentioned but no context on when to choose other tools like worm_seal.

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

worm_sealB

Seal any payload into the SnapKitty WORM chain with SHA-256. Every event is chained to the previous seal — tamper-evident, append-only.

ParametersJSON Schema

Name	Required	Description
`meta`	No	Optional metadata key-value pairs
`label`	Yes	Event label (e.g. DEPLOY, DECISION, CONTRACT)
`payload`	Yes	Data to seal — any string, JSON, code, or text

TDQS

B3.3/5.0

Behavior3/5

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

With no annotations, the description provides some behavioral context (append-only, tamper-evident, chained) but lacks details on side effects, permissions, limits, or return values.

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?

Two sentences, efficient and front-loaded with the core action. No wasted words.

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?

For a 3-parameter tool with full schema coverage and no output schema, the description is adequate but does not explain return behavior or complete operational context.

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 coverage is 100%, so baseline is 3. Description adds no specific parameter-level meaning beyond what the schema provides.

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 the tool seals a payload into a WORM chain using SHA-256, specifying the action and resource. It does not explicitly differentiate from sibling tools like worm_read, but the write nature is evident.

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?

No guidance on when to use this tool versus alternatives. It does not mention circumstances for use or exclusion, leaving the agent without context for selection decisions.

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

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

6 tool updatesv1.0.0Jun 28, 2026
- First observedada_contract_generate
- First observedagent_build
- First observedsovereign_inject
- First observedtwin_chat
- First observedworm_read
- First observedworm_seal

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.5/5.0

Disambiguation5/5

Each tool has a clear and distinct purpose: contract generation, agent building, SSM injection, twin chat, and WORM chain operations. No overlapping functionalities.

Naming Consistency4/5

Most tools follow a [noun]_[verb] pattern (e.g., twin_chat, worm_read), but ada_contract_generate uses [noun_noun_verb] and sovereign_inject uses [adjective_noun_verb], introducing slight inconsistency.

Tool Count5/5

With 6 tools, the server is well-scoped for its domain (contracts, agents, SSM injections, chat, and WORM chain). Not too many or too few.

Completeness4/5

Covers core operations (create, read, seal) for contracts, agents, and WORM chain. Minor gaps like missing update/delete for agents or contracts, but not critical for the intended use.

Maintenance

ActivityStale

ResponsivenessSyncing

Resources

GitHub Repository

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

runtime
com.formatho
Self-hosted MCP server: 26 deterministic dev, security, and EVM tools.
Developer Tools Blockchain Security
1
Word Of Clout ACN MCP Server
io.github.wordofclout
Guarded MCP server for agent-readable business truth, provenance, readiness, and discovery.
CRM Customer Data Platforms
2
The Quiet Protocol Growth Offense MCP A
com.thequietprotocol.www
Read-only MCP server for The Quiet Protocol's engines, benchmarks, proof, and business data.
Databases Research & Data Finance
292
BittensorMCPOAuth
io.github.btmcp
Hosted MCP server for live Bittensor chain reads and self-custodial on-chain writes.
Blockchain Cryptocurrency Web3 & Decentralized Tech
1

Related MCP Servers

IndigoProtocol/cardano-mcp
Blockchain Web3 & Decentralized Tech Finance
IndigoProtocol
A
license
Not graded
quality
C
maintenance
MCP server for Cardano blockchain data — exposes on-chain queries, address lookups, transaction history, token metadata, stake pool info, and network parameters to LLM agents.
Updated 4 months ago (2026-04-29 18:13 UTC)
105
4
MIT
math-logic-mcp
Code Execution Education & Learning Tools
ismailkerimov
A
license
A
quality
D
maintenance
MCP server that gives small LLMs verified symbolic-math & logic tools.
Updated 7 months ago (2026-02-20 12:40 UTC)
6
1
Apache 2.0
cardano-node-mcp
Blockchain Cryptocurrency Web3 & Decentralized Tech
michaeljfazio
A
license
Not graded
quality
D
maintenance
MCP server enabling LLMs to interact with a Cardano node by wrapping cardano-cli/torsten-cli, supporting queries, transactions, staking, and governance operations.
Updated 6 months ago (2026-03-15 16:04 UTC)
MIT
koios-mcp
Blockchain Cryptocurrency Web3 & Decentralized Tech
michaeljfazio
F
license
B
quality
D
maintenance
An MCP server that provides LLMs with access to 95 tools covering the Koios Cardano blockchain REST API, enabling queries for on-chain data like transactions, addresses, assets, and governance.
Updated 6 months ago (2026-03-10 12:24 UTC)
92
3
-

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

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/SNAPKITTYWEST/snapkitty-mcp'

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