A
licenseNot graded
qualityC
maintenanceLightweight MCP server for Portainer CE, focused on Docker Swarm environments with read-only tools by default and optional mutations.
MIT
dockhand-readonly-mcp
by cgfm
The dockhand-readonly-mcp server provides read-only access to a Dockhand-managed Docker environment, delivering sanitized insights while protecting sensitive information. All operations are safe, idempotent, and cannot modify resources. Key capabilities include:
dockhand_health: Check if the Dockhand service is reachable and healthy.
list_environments: List Docker environments with safe summaries (connection URLs and credentials omitted).
list_containers: List containers with identity, image, runtime health, ports, metrics, and network membership (optionally filtered by environment ID). Secrets, labels, mounts, logs, and commands are omitted.
get_container_summary: Get a sanitized summary for a single container by ID (never returns environment variables, labels, mounts, logs, commands, or raw inspect data).
list_networks: List networks with driver, internal flag, IPAM ranges, and sanitized container membership (optionally filtered by environment ID). Labels and driver options are omitted.
get_network_summary: Get a sanitized summary for a specific network by ID.
list_stacks: List stacks with names, states, types, and resource counts (optionally filtered by environment ID). Compose files, repository URLs, paths, and secrets are omitted.
get_runtime_overview: Get aggregate counts for containers, health, network isolation, and stack states for routine monitoring (optionally filtered by environment ID).
You cannot start, stop, restart, deploy, create, edit, or delete resources; access logs, terminals, or raw inspect data; or read environment variable values, Compose files, or credentials.
Click on "Install 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., "@dockhand-readonly-mcpshow me all running containers and their networks"
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.
Dockhand Read-only MCP
Read-only-MCP-Adapter für die Dockhand-REST-API. Das Projekt unterstützt zwei Transporte:
lokales STDIO für Codex auf demselben Rechner
authentifiziertes Streamable HTTP für den Docker-Betrieb
Sicherheitsgrenze
Dockhand Free kennt keine Viewer-Rolle. Der zugrunde liegende Dockhand-API-Token besitzt daher weiterhin die Rechte seines Dockhand-Benutzers. Der Adapter reduziert die für MCP erreichbare Oberfläche auf fest implementierte HTTP-GET-Abfragen:
Health, Umgebungen, Container, Netze und Stacks lesen
aggregierten Laufzeitstatus bilden
keine frei wählbaren URLs oder HTTP-Methoden
keine Start-, Stop-, Restart-, Deploy-, Create-, Edit- oder Delete-Werkzeuge
keine Logs, Terminals, ungefilterten Raw-Inspect-Daten oder Compose-Dateien
keine Ausgabe von Werten aus Umgebungsvariablen oder erkannten Zugangsdaten
explizite Security-Ansichten für Capabilities, Namespaces, Limits, Devices, Mount-Pfade, Port-Bindings, Netzwerkadressen, IPAM, Labels und Treiberoptionen; geheimnisverdächtige Label- und Optionswerte werden redigiert
Der Container erhält keinen Docker-Socket. Er kommuniziert ausschließlich über die Dockhand-REST-API. Der von Codex verwendete MCP-Bearer-Token ist ein zweites, unabhängiges Secret und darf nicht mit dem Dockhand-Token identisch sein.
Related MCP server: docker-mcp
Docker-Architektur
Codex
└─ HTTPS + separater MCP-Bearer-Token
└─ Reverse Proxy: mcp.example.com
└─ dockhand-readonly-mcp:3030
└─ konfiguriertes Docker-Netz + Dockhand-API-Token
└─ dockhand:3000/apiDer MCP-Adapter lauscht auf Port 3030; Dockhands eigener Standardport 3000 bleibt davon getrennt. Der MCP-Endpunkt ist /mcp. /healthz ist ohne Anmeldung erreichbar und liefert ausschließlich den Adapterstatus. Der Container prüft diesen Endpunkt alle 30 Sekunden. Alle MCP-Anfragen benötigen den separaten Bearer-Token.
Security-Prüfungen per MCP
Für eine Detailprüfung zuerst mit list_containers beziehungsweise list_networks die IDs ermitteln. Anschließend liefern:
get_container_security_config: gefilterte Docker-Inspect-Konfiguration mit Benutzer, Privilegien, Capabilities, Namespace-Modi, Security-Optionen, Ressourcenlimits, Devices, Mounts, Ports, DNS, Labels und Netzzuordnungenget_network_security_config: Netzwerk-Details mit Treiber, Flags, IPAM, Optionen, Labels, Peers sowie Endpoint-, MAC- und IP-Adressen
Die Werte von Umgebungsvariablen sowie Entrypoint- und Command-Argumente werden nicht ausgegeben. Sichtbar bleiben die Namen der Umgebungsvariablen und eine Liste der angewendeten Redaktionen.
Automatisches Container-Image auf GitHub
Der Workflow .github/workflows/publish-container.yml testet und baut das Image automatisch für linux/amd64 und linux/arm64. Bei jedem Push auf main wird es in der GitHub Container Registry veröffentlicht als:
ghcr.io/<github-owner>/<repository>:latestZusätzlich entstehen ein commitbezogener sha-...-Tag und bei Git-Tags wie v0.2.0 die Tags v0.2.0, 0.2.0 und 0.2. Pull Requests werden getestet und gebaut, aber nicht veröffentlicht.
Vor dem ersten Start:
Das Repository zu GitHub pushen. Der Workflow benötigt keine eigenen Registry-Secrets; er verwendet den automatisch bereitgestellten
GITHUB_TOKEN.Auf der GitHub-Paketseite das erzeugte Container-Paket öffentlich schalten. Soll es privat bleiben, muss der Docker-Host vor dem Abruf mit einem GitHub-Token mit
read:packagesanghcr.ioangemeldet werden.
Die Compose-Datei verwendet direkt das öffentliche Image ghcr.io/cgfm/dockhand_readonly_mcp:latest.
In Dockhand kann anschließend das GitHub-Repository als Stack-Quelle und compose.yaml als Compose-Datei gewählt werden. Dort müssen außerdem die Werte aus .env.example als Stack-Umgebungsvariablen hinterlegt werden. pull_policy: always sorgt dafür, dass bei einem erneuten Deploy das aktuelle Image aus GHCR abgerufen wird.
Deployment vorbereiten
Benutzer- und Gruppen-ID des Kontos bestimmen, dem die Secret-Dateien gehören:
id -u id -gZwei getrennte Secret-Dateien anlegen. Beide müssen diesem Benutzer gehören. Dateimodus
0600wird empfohlen; bei einem abweichenden Modus protokolliert der Adapter einmalig einen Hinweis, verwendet eine ansonsten gültige und lesbare Datei aber trotzdem:dockhand_api_token: vorhandener Dockhand-Token mit Präfixdh_mcp_bearer_token: neuer, zufälliger Zugriffstoken, beispielsweise ausopenssl rand -hex 32
.env.examplenach.envkopieren und Docker-Netz, Dockhand-URL, öffentliche MCP-Domain, PUID, PGID sowie die beiden absoluten Secret-Pfade anpassen. Keine Tokenwerte in.enveintragen. Unverschlüsseltes HTTP fürDOCKHAND_URLnur innerhalb eines vertrauenswürdigen privaten Docker-Netzes mitDOCKHAND_ALLOW_HTTP=trueaktivieren.Konfiguration prüfen und bereitstellen:
docker compose config docker compose pull docker compose up -d docker compose ps
Das Compose-Setup veröffentlicht keinen Host-Port. Der Reverse Proxy muss den Container über das in DOCKER_NETWORK konfigurierte externe Docker-Netz erreichen können.
Reverse Proxy
Beispielkonfiguration für Nginx Proxy Manager und mcp.example.com:
Feld | Wert |
Scheme |
|
Forward Hostname |
|
Forward Port |
|
Websocket Support | aktiviert |
SSL | Zertifikat, Force SSL, HTTP/2 |
Unter Advanced:
proxy_buffering off;
proxy_cache off;
proxy_read_timeout 3600s;
proxy_send_timeout 3600s;Der Proxy Host sollte nur aus Heimnetz und VPN erreichbar sein. Der Bearer-Token bleibt trotzdem verpflichtend.
Codex mit dem Container verbinden
Den MCP-Bearer-Token im lokalen Prozessumfeld von Codex als DOCKHAND_MCP_BEARER_TOKEN bereitstellen und danach registrieren:
codex mcp add dockhand-readonly \
--url https://mcp.example.com/mcp \
--bearer-token-env-var DOCKHAND_MCP_BEARER_TOKENDie vorhandene STDIO-Konfiguration erst entfernen, nachdem die HTTP-Variante getestet wurde. Codex unterstützt für Streamable-HTTP-MCPs Bearer-Tokens aus einer benannten Umgebungsvariable; der Tokenwert gehört nicht in config.toml.
Lokaler STDIO-Betrieb
[mcp_servers.dockhand-readonly]
command = "node"
args = ["/absolute/path/to/src/server.mjs"]
[mcp_servers.dockhand-readonly.env]
DOCKHAND_URL = "https://dockhand.example.com"
DOCKHAND_TOKEN_FILE = "/absolute/path/to/dockhand-token"Tests
npm ci
npm test
npm run live-check
docker build -t local/dockhand-readonly-mcp:0.2.0 .Available Tools
8 toolsdockhand_healthCheck Dockhand healthARead-onlyIdempotent
Checks whether the configured Dockhand service is reachable and healthy.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
TDQS
A4.2/5.0
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds 'configured' and 'reachable and healthy' but does not disclose additional behavioral traits such as error handling, return format, or what happens if the service is unhealthy.
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 sentence, front-loaded with the action, and contains zero waste. Every word earns its place.
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 zero-parameter, no-output-schema tool, the single-sentence description is largely sufficient. It could specify what a negative result means or the response format, but given the simplicity and annotations, it is nearly complete, warranting a 4 rather than 5.
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, so schema coverage is 100% vacuously. With zero parameters, the description need not add parameter syntax or meaning, and the baseline of 4 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 uses a specific verb 'checks' and resource 'configured Dockhand service' with the outcome 'reachable and healthy'. This clearly distinguishes it from sibling tools that list or get individual resources.
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?
The description implies this is for verifying the service's health, and all sibling tools are list/get operations, providing clear context. However, it does not explicitly state when not to use it or name alternative tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_container_summaryGet a Docker container summaryARead-onlyIdempotent
Gets a sanitized summary for one container ID returned by list_containers. It never returns environment variables, labels, mounts, logs, commands, or raw inspect data.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| container_id | Yes | ||
| environment_id | No | Optional Dockhand environment ID from list_environments. |
TDQS
A4.4/5.0
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond annotations (readOnlyHint, idempotentHint), the description explicitly lists what it never returns (environment variables, labels, mounts, logs, commands, raw inspect data), which is critical behavioral context for a Docker inspection 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?
Two sentences that are dense with information—purpose and exclusions—with no redundant wording.
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?
Adequate for a simple read-only tool with annotations: it states the scope (one container) and sanitization exclusions. Missing a preview of what the summary includes, but no output schema exists.
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 description clarifies that container_id must be one returned by list_containers, adding provenance meaning. environment_id already has a description in the schema, covering the other parameter.
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?
Clearly states it gets a sanitized summary for one container ID, making the verb and resource explicit. It also distinguishes itself from siblings by referencing list_containers and omitting sensitive data.
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?
Clear context: use for one container ID returned by list_containers. It implies a preceding list_containers call but doesn't explicitly state when not to use or mention alternatives like get_network_summary.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_network_summaryGet a Docker network summaryARead-onlyIdempotent
Gets a sanitized summary for one network ID returned by list_networks.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| network_id | Yes | ||
| environment_id | No | Optional Dockhand environment ID from list_environments. |
TDQS
A4/5.0
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish read-only, idempotent, non-destructive behavior. The description adds the 'sanitized' detail and the constraint that the ID comes from list_networks, providing some context but not covering error behavior 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.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, front-loaded with the core action, no redundancy.
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?
With strong annotations and a simple parameter set, the description provides adequate context for a read-only summary tool. It doesn't detail return values or error cases, but those are less critical given the tool's simplicity.
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 50%: network_id lacks a description, but the tool description clarifies it must come from list_networks. environment_id is described in the schema. The description partially compensates for the missing schema doc but doesn't add syntax details.
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 clearly states the tool retrieves a sanitized summary for a single network ID, with the ID sourced from list_networks. This specific verb+resource+scope distinguishes it from sibling tools like list_networks (which lists) and get_container_summary (which targets containers).
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?
The description implies usage after calling list_networks, providing a clear workflow. It does not explicitly state when not to use it, but the context is sufficient for an agent to select it for single-network inspection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_runtime_overviewSummarize Docker runtimeARead-onlyIdempotent
Returns aggregate container, health, network-isolation, and stack-state counts for routine monitoring.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| environment_id | No | Optional Dockhand environment ID from list_environments. |
TDQS
A4/5.0
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is well covered. The description adds minimal behavioral context beyond stating it returns aggregate counts; it does not mention environment scoping or response structure, but this is acceptable given annotation coverage.
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, front-loaded sentence that efficiently conveys the tool's essence without any waste. Every word contributes to understanding the purpose and scope.
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?
Given the tool's low complexity (one optional parameter, no output schema), the description adequately covers the main function and return categories. It omits mention of the optional environment_id filter, but that is already fully documented in the schema, so the overall context is sufficiently complete.
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% for the single optional parameter, environment_id, which is fully described as an optional Dockhand environment ID from list_environments. The tool description adds no additional meaning beyond the schema, so the baseline of 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 uses a specific verb ('Returns') and resource scope ('aggregate container, health, network-isolation, and stack-state counts'), clearly distinguishing this aggregate overview tool from sibling list/detail tools like list_containers, get_container_summary, and list_stacks.
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?
The phrase 'for routine monitoring' provides clear context for when to use the tool. It implies this is for high-level aggregate checks rather than detailed troubleshooting, and the sibling tool names reinforce the distinction, though no explicit exclusions or alternatives are named.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
list_containersList Docker containersARead-onlyIdempotent
Lists container identity, image, runtime health, ports, metrics, and network membership. Secrets, labels, mounts, logs, and commands are omitted.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| environment_id | No | Optional Dockhand environment ID from list_environments. |
TDQS
A3.8/5.0
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is well covered. The description adds field-level transparency by stating exactly what is included and omitted, giving a clear expectation of the response content beyond what annotations provide.
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 two sentences, tightly packed with relevant information. The first sentence front-loads the verb, resource, and key data categories; the second sentence crisply lists what is omitted. No wasted words or duplication of schema/annotation data.
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?
The tool has low complexity (one optional parameter, safe read operation) and rich annotations. The description adequately covers the return scope and omissions. It does not mention default behavior when environment_id is omitted or pagination, but these are minor gaps for a simple list tool.
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 for parameters is 100% and the only parameter, environment_id, is already described in the schema as 'Optional Dockhand environment ID from list_environments.' The description adds no additional parameter semantics, so the baseline score of 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 uses the specific verb 'Lists' with resource 'containers' and clearly enumerates the included fields (identity, image, runtime health, ports, metrics, network membership) and excluded fields (secrets, labels, mounts, logs, commands). This scope distinguishes it from sibling tools like get_container_summary and list_networks.
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?
The description provides no guidance on when to use this tool versus alternatives. It does not mention any when-not conditions, such as needing secrets/labels/mounts, nor does it point to get_container_summary or list_networks for those cases.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
list_environmentsList Docker environmentsARead-onlyIdempotent
Lists safe summaries of Docker environments known to Dockhand. Connection URLs and credentials are omitted.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
TDQS
A4.1/5.0
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, and non-destructive behavior. The description adds valuable security context by stating that connection URLs and credentials are omitted, which is a behavioral trait beyond the annotations.
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 two short sentences, front-loaded with the action 'Lists'. Every word earns its place, with no redundant information or filler.
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 zero-parameter, read-only list tool, the description covers what it does and its key security behavior. Combined with the annotations, an agent has sufficient context to use it correctly without needing further output details.
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 input schema is empty (0 parameters), so the baseline is 4. The description does not need to add parameter details, and the security note about omitted credentials provides relevant context for understanding the output.
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 clearly states it lists Docker environments known to Dockhand, using a specific verb ('lists') and resource ('Docker environments'). The added detail about safe summaries (omitting credentials) further clarifies its scope and distinguishes it from sibling tools like list_containers or list_networks.
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?
The description provides no guidance on when to use this tool versus alternatives. It does not mention sibling tools, exclusions, or specific conditions for use, leaving the agent to infer from the tool name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
list_networksList Docker networksARead-onlyIdempotent
Lists network driver, internal flag, IPAM ranges, and sanitized container membership. Labels and driver options are omitted.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| environment_id | No | Optional Dockhand environment ID from list_environments. |
TDQS
A3.8/5.0
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark the tool as read-only, idempotent, and non-destructive. The description adds valuable behavioral context beyond annotations: it states that container membership is 'sanitized' and that labels and driver options are omitted. This informs the agent about data fidelity and privacy/security handling, which is helpful for interpreting results.
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 two sentences with zero fluff. It front-loads the core purpose and adds a single clarification about exclusions. Every word contributes to understanding the tool's behavior.
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?
Given a simple list operation with one optional parameter, no output schema, and strong annotations, the description sufficiently covers what the tool does and what it returns. It mentions omissions and sanitization. It doesn't explain the effect of environment_id or output format, but the schema covers the parameter and the tool is straightforward, so the description is reasonably complete.
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 input schema already covers the single parameter (environment_id) with a description and pattern, achieving 100% schema description coverage. The description does not mention the parameter or add any usage semantics beyond what the schema provides, so the baseline score of 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 the tool lists network-related information (driver, internal flag, IPAM ranges, and sanitized container membership) and explicitly notes what is omitted (labels and driver options). It identifies the resource (Docker networks) and the verb (lists), but does not explicitly distinguish it from sibling tools like get_network_summary, so it doesn't fully earn 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 Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Usage is implied through the listed fields: if you need network driver, internal flag, IPAM ranges, or container membership, this tool provides them. However, there is no explicit guidance on when to use this tool versus alternatives like get_network_summary, nor any mention of environment filtering despite the optional environment_id parameter. The context signals reveal siblings but the description itself gives no comparative direction.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
list_stacksList Docker stacksARead-onlyIdempotent
Lists stack names, states, types, and resource counts. Compose files, repository URLs, paths, and secrets are omitted.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| environment_id | No | Optional Dockhand environment ID from list_environments. |
TDQS
A4.2/5.0
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and destructiveHint false, so the safety profile is established. The description adds value by detailing the fields returned and specifically noting that sensitive data (compose files, repository URLs, paths, secrets) are omitted, which helps set expectations. It does not introduce contradictions and provides useful behavioral context beyond the annotations.
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 two sentences long and immediately states the core purpose in the first sentence. The second sentence adds a critical exclusion note. Every word earns its place; there is no fluff or redundancy.
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-only tool with one optional parameter and no output schema, the description adequately conveys the return fields. It covers the essentials and the schema fills in the environment_id behavior. It does not mention pagination or filtering specifics, but those are implied by the parameter description and the tool's simplicity, so it is sufficiently complete.
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 already describes the only parameter (environment_id) with 100% coverage, including a note that it is from list_environments. The tool description does not add any further parameter semantics beyond what the schema provides, so a baseline score of 3 is appropriate.
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 clearly states the tool lists stack names, states, types, and resource counts, using a specific verb ('lists') and resource ('stacks'). It distinguishes from sibling tools by focusing exclusively on stacks and explicitly noting what is omitted (compose files, repository URLs, paths, secrets), making the scope unmistakable.
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?
The description implies usage by outlining the exact information returned, making it clear when to use this tool for stack summaries. It does not explicitly mention alternatives or exclusions, but the singular focus on stacks and the optional environment_id parameter (which references list_environments) provide practical context for filtering. The absence of explicit 'when not to use' guidance is a minor gap.
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.
8 tool updates
v0.2.0- First observed
dockhand_health - First observed
get_container_summary - First observed
get_network_summary - First observed
get_runtime_overview - First observed
list_containers - First observed
list_environments - First observed
list_networks - First observed
list_stacks
TDQS
A4.1/5.0
Disambiguation5/5
Each tool has a distinct purpose: health check, list environments, list containers, get one container, list networks, get one network, list stacks, and aggregate overview. The list vs. get pairing for containers and networks prevents confusion, and the overview and health tools are uniquely scoped.
Naming Consistency4/5
Most tools follow a consistent verb_noun pattern (list_*, get_*, get_*_summary). The outlier is dockhand_health, which reads as a noun phrase rather than a verb-based action, but it is still understandable and does not break the overall pattern significantly.
Tool Count5/5
With 8 tools, this server is well-scoped for a read-only Docker inspection and monitoring service. Each tool covers a necessary facet (environments, containers, networks, stacks, health, and overview) without redundancy or bloat.
Completeness4/5
The server covers the main read-only monitoring operations: listing and summarizing containers and networks, listing stacks and environments, plus a health check and runtime overview. A get_stack_summary or get_environment_summary could be expected, but their absence seems intentional for security/sanitization reasons, and the core workflows are covered.
Maintenance
ActivityMaintained
ResponsivenessSyncing
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Docker Hub MCP — wraps the Docker Hub v2 API (free, no auth required for public data)
Read-only MCP server for turva.dev, an agent-readiness audit and advisory service.
Read-only MCP access to a documented IT fleet: state, changes, posture. 15 tools.
Read-only MCP server for The Quiet Protocol's engines, benchmarks, proof, and business data.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceA read-only MCP server that exposes your Docker daemon, allowing AI assistants to list containers, inspect their details, and fetch logs without write access.-
- FlicenseNot gradedqualityCmaintenanceRead-only MCP adapter for BookStack REST API. Enables listing and searching shelves, books, chapters, and pages while enforcing least-privilege access.-
- AlicenseNot gradedqualityCmaintenanceRead-only MCP server to inspect allowlisted Docker containers, systemd services, JSONL logs, and HTTP health endpoints without arbitrary shell access.MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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/cgfm/dockhand_readonly_mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server