A
licenseNot graded
qualityC
maintenanceA secure, production-grade MCP server that provides filesystem operations, AST math evaluation, and system diagnostics for LLM agents.
MIT
Msty Local Ops
Officialby vega-llc
This server provides read-only diagnostics for Msty Studio on macOS, exposing four tools to inspect installation health, service readiness, and model availability without accessing private data.
get_msty_status — Reports installation state, local-service availability, and overall readiness.
get_capability_manifest — Describes the diagnostic surface and trust boundaries.
get_model_manifest — Lists model facts from loopback-only local model services.
run_compatibility_check — Validates the installed Msty Studio version and local model endpoint schemas.
A separate opt-in local-inference process can expose a
local_generatetool.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Msty Local Opscheck the current Msty status and compatibility"
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.
Msty Local Ops
Msty Local Ops is a small, fail-closed MCP for Msty Studio on macOS. It exposes four read-only diagnostics and, in a separate opt-in process, one bounded local-generation tool. It does not read chats, Knowledge Stacks, private databases, provider keys, or application configuration.
New here? Start with the illustrated Mac start guide.
This is an independent community project, not an official Msty product.
What you get
The default diagnostic process exposes exactly:
get_msty_statusget_capability_manifestget_model_manifestrun_compatibility_check
The separate local-inference process adds only local_generate. That tool requires
an exact model identifier advertised by a fixed Msty loopback service. It never
auto-selects a model, follows redirects, uses a proxy, or falls back to an online
provider. Its bounded thinking_mode option accepts only default or none;
none sends the standard local chat-template switch without exposing arbitrary
provider parameters.
Related MCP server: apple-fm-mcp
Install
Install Msty Studio for macOS.
Install Python 3.10, 3.11, or 3.12. The installer selects a supported version even when a newer
python3is also installed.Download this repository and double-click
Install Msty Local Ops.command.The installer creates two ready-to-paste Toolbox JSON files and opens their folder.
In Msty Studio, open Toolbox → Add New Tool → STDIO / JSON and paste the diagnostic JSON first.
Test the tool in Msty's Tool Console before attaching it to a conversation.
Msty starts the MCP when it needs it. There is no background service to launch by hand. After installation, start Msty Studio first.
Msty's official Toolbox guide explains the same local STDIO/JSON flow: Msty Studio Tools.
The diagnostic MCP is the safe default. Add the local-inference JSON only when you want the calling model to send prompts to a local Msty model. The calling MCP client can observe those prompts and results; see PRIVACY.md.
Health, upgrade drift, and support
The installer adds two local commands:
msty-local-ops-doctor
msty-local-ops-support --output msty-local-ops-support.json
msty-local-ops-verifyThe doctor reports GREEN, YELLOW, or RED and never reads chats, keys, or
Msty's private database. After a known-good setup, run
msty-local-ops-doctor --record-baseline. Future checks warn if the tested Studio
version, adapter version, or local service shape changes.
The support command writes a mode-0600 JSON bundle containing versions, booleans, counts, and error categories only. It deliberately excludes usernames, paths, model identifiers, prompts, content, provider details, and credentials. Review the file before attaching it to a public issue.
The verify command is diagnostic by default and submits no prompt. To run the fixed public/synthetic inference canary, explicitly name an advertised local model and its service:
msty-local-ops-verify --model "<exact-local-model-id>" --service mlx --jsonThe canary never accepts document content or a custom prompt and never falls back to an online provider.
Try the fictional Knowledge Stack
The folder examples/knowledge-stack/synthetic-canary contains a completely
fictional retrieval test. It includes a controlling handbook, an obsolete source, an
incident clarification, and an adversarial note.
In Msty, create a Knowledge Stack.
Add the entire
synthetic-canaryfolder.Choose a local embedding model if you want processing to remain on the device.
Compose the stack and attach it to a chat using a local model.
Run the questions in docs/KNOWLEDGE_STACK.md.
Official references: Knowledge Stack basics and local models.
Network and data boundary
The adapter has only these destinations:
Msty service | Address |
Local AI |
|
MLX |
|
llama.cpp |
|
Only GET /v1/models and POST /v1/chat/completions are permitted. The default
diagnostic process never submits prompts.
Development
python3 -m venv .venv
.venv/bin/python -m pip install -e '.[dev]'
.venv/bin/python -m pytest -q
.venv/bin/python scripts/check_public_boundary.py .
uv lock --check
uv export --frozen --no-dev --no-emit-project --format requirements.txt --output-file requirements-audit.txtThe public repository must start with a fresh initial commit. Do not merge or import history from an operational or private repository.
License and attribution
Available Tools
4 toolsget_capability_manifestB
Report the exact four-tool diagnostic surface and its trust boundaries.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Output Schema
ParametersJSON Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
TDQS
B3/5.0
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden for behavioral disclosure. It does not mention whether the tool is read-only, has side effects, or what 'trust boundaries' entail in a behavioral sense, leaving the agent without important safety and execution context.
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 a single clear sentence with no filler words, typical of a concise tool definition. However, it is terse to the point of omitting useful context, so not a 5.
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?
Despite an output schema existing, the description does not explain what the 'four-tool diagnostic surface' refers to, how it relates to sibling tools, or what 'trust boundaries' means in practice. The tool's purpose seems specialized, and the description provides insufficient contextual grounding for an agent to decide when to invoke it.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters, so the description cannot add parameter-level meaning. The baseline for 0 params is 4, and the description does not detract from this.
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 uses the specific verb 'Report' and names a concrete resource ('exact four-tool diagnostic surface and its trust boundaries'), distinguishing it from sibling tools. However, 'four-tool diagnostic surface' is somewhat cryptic without elaboration, preventing a 5.
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 given on when to use this tool versus alternatives, nor any exclusions or prerequisites. The description only states what the tool reports, not when it is appropriate to call it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_model_manifestA
List facts advertised by fixed, loopback-only Msty model services.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Output Schema
ParametersJSON Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
TDQS
A3.8/5.0
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden. It does indicate a read-only 'List' operation and the 'loopback-only' scoping constraint, which is useful. However, it does not disclose details like default behavior, error conditions, or what 'facts' entails beyond the output schema.
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 a single, focused sentence. It is front-loaded with the action and resource, with no wasted words.
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 no-parameter, read-only list operation with an output schema, the description is mostly complete. It could benefit from clarifying what categories of facts are advertised, but the output schema likely covers that. The tool's simplicity warrants a high score.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has no parameters and the schema coverage is 100% (vacuously). The description adds no parameter-specific information that is needed since none exist, meeting the baseline for a zero-parameter tool.
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 uses a specific verb 'List' and identifies the resource: 'facts advertised by fixed, loopback-only Msty model services.' This clearly distinguishes it from siblings like get_capability_manifest and get_msty_status.
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 given on when to use this tool versus the listed sibling tools. The description implies its scope (fixed loopback-only model services) but does not explicitly mention alternatives or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_msty_statusA
Report installation, local-service, and readiness state without reading Msty data.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Output Schema
ParametersJSON Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
TDQS
A4.1/5.0
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the behavioral disclosure burden. It discloses that the tool does not read Msty data, suggesting a non-invasive operation. However, it does not explicitly state that it has no side effects, require no permissions, or describe failure modes, leaving some gaps.
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 a single concise sentence that front-loads the core purpose and adds a valuable qualifier without unnecessary words. Every word earns its place.
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 simple zero-parameter status check with an output schema, the description covers the essential purpose and a key behavioral constraint. It does not need to explain return values because the output schema exists, and there are no parameters to document.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool accepts zero parameters, making the schema trivially complete. Per the rubric, zero parameters receive a baseline of 4, and there is nothing meaningful to add in the description regarding parameters.
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 uses the verb 'Report' and specifies concrete resources: installation, local-service, and readiness state. This clearly distinguishes it from sibling tools like get_capability_manifest or run_compatibility_check, which target different aspects.
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 context about what the tool does and a key qualifier ('without reading Msty data'), but it does not explicitly state when to prefer this tool over alternatives or mention exclusions. The differentiation from siblings is implicit rather than explicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
run_compatibility_checkA
Validate the installed Studio version and local model endpoint schemas.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Output Schema
ParametersJSON Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
TDQS
A3.6/5.0
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description must carry the burden of behavioral disclosure. It does not mention whether the validation is read-only, what happens on failure, or any side effects. The verb 'Validate' implies a check but lacks explicit behavioral context.
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 a single, clear sentence that is front-loaded with the verb and target subjects. It is appropriately concise with no wasted words.
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 tool with no parameters and an output schema, the description adequately covers the tool's purpose. However, it lacks context on when to use the tool or what the validation report conveys, though the output schema may supply that.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters, so schema coverage is 100% by default. The description adds no parameter details, but none are needed since there are no inputs.
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 action ('Validate') with clear targets ('installed Studio version' and 'local model endpoint schemas'), distinguishing it from sibling getter tools like get_msty_status or get_model_manifest.
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 the sibling tools, nor any prerequisites or conditions that would trigger its use. The description only states what it does.
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.
4 tool updates
v1.2.0- First observed
get_capability_manifest - First observed
get_model_manifest - First observed
get_msty_status - First observed
run_compatibility_check
TDQS
A3.9/5.0
Scored across 4 tools
Disambiguation5/5
Each tool targets a distinct aspect: status, capability manifest, model manifest, and compatibility check. There is no overlap; even the two manifest tools are clearly separated by domain (tool surface vs. model services).
Naming Consistency5/5
All names follow a consistent verb_noun snake_case pattern, with three 'get_' verbs and one 'run_' verb, which is a natural fit for a validation operation. The naming is predictable and readable.
Tool Count5/5
Four tools is well-scoped for a diagnostic server focused on local ops status, capabilities, models, and compatibility. Each tool earns its place without bloat or thinness.
Completeness5/5
The tool set forms a complete diagnostic surface: status, capability manifest, model manifest, and compatibility validation. The inclusion of a capability manifest explicitly confirms the surface is intentionally limited to these four tools, so no obvious gaps exist.
Maintenance
ActivitySlowing
ResponsivenessNo issues
Related MCP Connectors
MCP server for secureFlows: token-free URL builders and integration-linting tools for AI agents.
An MCP server that provides read access to your cloud storage providers, bank accounts and more.
A paid remote MCP for CLI tool MCP, built to return verdicts, receipts, usage logs, and audit-ready
Read-only MCP server for AIStatusDashboard status, incidents, metrics, and fallback recommendations.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceMCP server that enables local Apple on-device Foundation Model access via any MCP client, supporting text generation, structured output, and multi-turn chat on macOS.2MIT
- AlicenseBqualityAmaintenanceA local MCP server that lets compatible agents use the official, signed Computer Use broker bundled with the OpenAI ChatGPT macOS app.1117513MIT
- AlicenseNot gradedqualityAmaintenanceA macOS-native MCP server that provides AI hosts with fresh workspace state, bounded context, and retained execution evidence, avoiding collapsing operations into shell strings.3221Apache 2.0