mulewatch
Provides read-only observability for MuleSoft Anypoint Platform, allowing agents to inspect application logs, search historical archived logs, and query Runtime Manager, API Manager, and Exchange assets across business groups and environments.
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., "@mulewatchshow me recent errors from the production payment API logs"
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.
What it does
mulewatch bridges an MCP client — Claude Desktop, Claude Code, Cursor, OpenClaw — to MuleSoft Anypoint Platform, so you can ask about a Mule estate in plain language and get real answers from the platform APIs. It is aimed at the person holding the pager, not the person writing the flow: no local Mule project is required, and every tool is read-only.
Application logs from Runtime Manager, normalized across CloudHub 2.0, Runtime Fabric and legacy CloudHub.
Historical log search through the Anypoint Monitoring Archive API, reaching incidents long past the live tail's rolling buffer.
Analysis-ready log payloads — normalized lines plus counts by priority, logger and replica.
Runtime Manager inventory across Application Manager, CloudHub and hybrid on-prem targets.
API Manager instances and Exchange assets, so a single server answers "what is deployed, what is it fronted by, and what broke".
Nothing is hardcoded to one customer: business groups, environments and credentials all come from your own connected app.
How this relates to the official MuleSoft MCP server
MuleSoft publishes its own MCP server (mulesoft-mcp-server, docs). It is a development tool — it scaffolds Mule projects, generates flows and API specs, and deploys applications, largely from a local project in an IDE.
mulewatch is an operations tool. It never writes to your estate, it assumes no local project, and it covers the one area the official server does not address at all: retrieving and searching application logs, including historical logs from the Monitoring Archive. The two run happily side by side, and if you want deployment or scaffolding tools, use the official one.
Related MCP server: LGTM MCP Server
Requirements
Node.js 20+
An Anypoint Platform account with access to the business group you want to read
A connected app (recommended) with "acts on its own behalf" enabled, or platform credentials
For historical log search only: Anypoint Monitoring enabled for the organization
Connected-app scopes
Grant the scopes for the surfaces you intend to use, on the business groups and environments you care about. Anypoint returns a bare 403 Forbidden when a scope is missing; mulewatch catches that and names the scope you probably need.
Surface | Scope |
Environments, business groups |
|
Runtime Manager apps and logs |
|
Historical archive search | Anypoint Monitoring |
API Manager instances |
|
Exchange assets | Exchange viewer access |
Setup
Create a connected app in Anypoint Platform → Access Management → Connected Apps, choose "App acts on its own behalf (client credentials)", grant the scopes above, and copy the client id and secret.
Configuration is environment variables only — there is no config file and no organization default.
ANYPOINT_CLIENT_ID=your_connected_app_client_id
ANYPOINT_CLIENT_SECRET=your_connected_app_client_secretVariable | Required | Purpose |
| one auth method | Connected app client credentials, preferred for automation |
| one auth method | Platform login |
| one auth method | Pre-generated bearer token; takes precedence over the other two |
| no | Business group id. Unset means "the organization the credentials belong to" |
| no | Comma-separated environment names or ids; when set, every tool refuses anything outside the list |
| no | Control plane host, defaults to |
| no | Monitoring host, defaults to |
Business groups
Environments live on business groups, not on the root organization. If anypoint_list_environments comes back empty, your credentials resolved to the root org — call anypoint_list_business_groups to list the ids, then pass one as orgId or pin it with ANYPOINT_ORG_ID.
Keeping production out of reach
ANYPOINT_ALLOWED_ENVIRONMENTS scopes the whole server, not one tool. With
ANYPOINT_ALLOWED_ENVIRONMENTS=Dev,Sandboxevery tool refuses an environment outside the list and says why, whichever business group is targeted. Combine it with a connected app that only has access to those environments for defence in depth.
Run
Nothing to install — point your MCP client at npx:
{
"mcpServers": {
"mulewatch": {
"command": "npx",
"args": ["-y", "mulewatch"],
"env": {
"ANYPOINT_CLIENT_ID": "your_connected_app_client_id",
"ANYPOINT_CLIENT_SECRET": "your_connected_app_client_secret"
}
}
}
}That block works as-is in Claude Desktop (claude_desktop_config.json), Cursor (.cursor/mcp.json) and OpenClaw. For Claude Code:
claude mcp add mulewatch --env ANYPOINT_CLIENT_ID=... --env ANYPOINT_CLIENT_SECRET=... -- npx -y mulewatchFrom a clone instead:
npm install
npm run build
npm startThe server speaks stdio, which is what MCP clients expect. Start with anypoint_whoami to confirm credentials, business group and scope before anything else.
Tools
Every tool is read-only. All of them accept orgId to override the configured business group.
anypoint_whoami
Confirms which credentials, business group, hosts and environment allowlist the server is running with. No arguments. Call this first when anything fails.
anypoint_list_business_groups
Lists the business groups beneath the credentials' organization, with ids and nesting depth.
{ "rootOrgId": "optional-root-organization-id" }anypoint_list_environments
Lists environments for a business group, filtered by ANYPOINT_ALLOWED_ENVIRONMENTS when set.
{ "orgId": "your-business-group-id" }anypoint_list_deployed_apps
Lists deployed Mule applications for an environment, by environmentId or environmentName.
{ "environmentName": "Dev", "target": "all" }Option | Purpose |
|
|
| Maximum records to return, default |
| Include raw API objects in the response |
| Include per-target errors when a target endpoint is unavailable or not permitted |
application_manager covers CloudHub 2.0 and Runtime Fabric deployments, cloudhub legacy CloudHub, hybrid on-prem Runtime Manager. all queries every target and reports per-target failures instead of aborting.
anypoint_list_app_logs
Lists the latest Runtime Manager logs for an application.
{ "environmentName": "Dev", "appName": "my-mule-app" }Option | Purpose |
| Use instead of |
| Use when the app name is ambiguous or already known |
| A specific Application Manager deployment spec/config id |
|
|
| Maximum log entries, default |
| Application Manager log offset, default |
| Latest first, default |
| Application Manager time filter, ISO 8601 |
| Include the raw API response |
| Include failed target errors when |
For CloudHub 2.0 and Runtime Fabric the tool resolves appName to a deployment, resolves the current spec, then reads that spec's logs. For legacy CloudHub it calls the CloudHub logs endpoint directly.
anypoint_get_app_logs_for_analysis
Same sources as above, but returns an analysis-ready payload rather than a raw list. Prefer it when diagnosing something.
{ "environmentName": "Dev", "appName": "my-mule-app", "limit": 200, "errorOnly": true }Takes every option of anypoint_list_app_logs, plus:
Option | Purpose |
| Case-insensitive filters matched against timestamp, priority, message, logger, thread or instance |
| Only return |
The response carries analysis.totalFetched, analysis.totalMatched, analysis.priorityCounts, analysis.loggerCounts, analysis.instanceCounts and analysis.logs. Counts describe everything fetched; logs holds what matched.
anypoint_search_archived_logs
Searches historical logs through the Anypoint Monitoring Archive API, for dates beyond what the live tail can see.
This is the tool the others cannot replace. anypoint_list_app_logs and anypoint_get_app_logs_for_analysis read Runtime Manager's live tail — a small rolling buffer that can scroll out within minutes on a busy application, no matter what startTime/endTime you pass. The archive lands files roughly ten minutes after each ten-minute window closes and keeps them far longer.
Requires Anypoint Monitoring to be enabled for the organization. Without it every call 403s or 404s; fall back to a manual Download Logs export from the Runtime Manager UI.
{
"environmentName": "Prod",
"appName": "my-mule-app",
"date": "2026-08-09",
"searchTerms": ["Started product import", "Import finished"]
}Option | Purpose |
| Required, |
| Optional inclusive range end, |
| Case-insensitive text filters |
| Only return |
| Cap on replica entities probed during a full-scan fallback, default |
| Cap on archive files downloaded and parsed, default |
| Cap on matched lines returned, default |
| Include the raw parsed entry alongside the normalized fields |
How it finds your logs. The Archive API indexes per replica/pod ({appName}_{replicaId}), not per application, so the replica has to be identified before anything can be read. mulewatch first tries the replica ids visible in the live Runtime Manager tail (entityResolution: "live-replica") — pods are usually long-lived between redeploys, so that same replica normally produced the logs on recent past dates too, and a typical lookup costs a handful of archive calls. If that replica has no files for the requested dates — the application was redeployed since, say — it falls back to listing every replica the app has ever had and probing each (entityResolution: "full-scan"), bounded by maxEntities.
The Archive API allows 60 requests/minute; the client throttles beneath that and backs off on 429. A full-scan fallback across many replicas can take a while, so narrow the date range where you can. The response reports which path was taken and whether any cap truncated the result.
anypoint_list_api_manager_instances
Lists API instances managed by API Manager in an environment.
{ "environmentName": "Dev", "assetId": "my-api" }Option | Purpose |
| Filter by Exchange asset id |
| Filter by technology, e.g. |
| Pagination, default |
| Include raw API objects |
anypoint_search_exchange_assets
Searches Anypoint Exchange for assets in the organization.
{ "search": "customer", "types": ["rest-api"], "limit": 20 }Option | Purpose |
| Free-text search over asset names and descriptions |
| Filter by asset type, e.g. |
| Pagination, default |
| Include raw API objects |
Tech stack
Layer | Technology |
Runtime | Node.js 20+, ES modules |
Language | TypeScript 5.7, |
Protocol | Model Context Protocol SDK 1.30, |
Validation | zod 4 |
Auth | Anypoint |
Tests |
|
Repository layout
.
├── src/
│ ├── index.ts # bin entry: config check, stdio wiring
│ ├── tools.ts # MCP tool registration and argument schemas
│ ├── client.ts # AnypointClient: auth, org resolution, all API calls
│ ├── config.ts # env-var config, environment allowlist
│ ├── normalize.ts # envelope unwrapping, log normalization, analysis
│ ├── archive-parse.ts # archive log line parsing, date range enumeration
│ └── errors.ts # AnypointApiError and message formatting
├── test/ # unit tests for the pure logic
├── docs/logo.png # project mark, used in this README
├── server.json # MCP registry manifest
└── .env.exampleVerification status
Read paths were exercised against a live Anypoint organization during development:
Tool | Status |
| Verified live |
| Verified live |
| Verified live |
| Verified live ( |
| Verified live (Application Manager path) |
| Verified live (Application Manager path) |
| Verified live |
| Verified live — both the |
| Not verified — the test connected app lacked the |
On the application used for that check, the archive held 669 historical replica entities. Searching the current day resolved through the live-replica fast path and probed one of them, finding 127 archive files and parsing 2,859 log lines. Searching a date from before the last redeploy correctly fell through to the full-scan path, which is the slow case the maxEntities cap exists to bound.
Notes
Every tool is read-only. There are no deploy, stop, restart or policy-mutation tools, by design — an LLM should not be mutating a production Mule estate, and the official MuleSoft server already covers deployment.
Tokens are cached in memory until a minute before expiry and never written to disk.
Credentials are read from the environment only; nothing is logged.
Anypoint returns bare
403s for missing connected-app scopes. Those are caught and annotated with the scope that is probably missing.EU and other control planes work by overriding
ANYPOINT_BASE_URLandANYPOINT_MONITORING_BASE_URL.
License
Apache-2.0. MuleSoft, Anypoint Platform and CloudHub are trademarks of Salesforce, Inc.; this is an independent project and is not affiliated with or endorsed by Salesforce.
Available Tools
9 toolsanypoint_get_app_logs_for_analysisAnalyze application logsA
Fetch live-tail logs for a Mule application and return an analysis-ready payload: normalized lines plus counts by priority, logger and instance. Prefer this over anypoint_list_app_logs when diagnosing a problem.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum log entries, default 100, max 500. | |
| orgId | No | Business group id. Defaults to ANYPOINT_ORG_ID, or the credentials' own organization. | |
| offset | No | Application Manager log offset, default 0. | |
| specId | No | Specific Application Manager deployment spec/config id. | |
| target | No | Log source. Defaults to auto, which tries Application Manager then CloudHub. | |
| appName | Yes | Deployment/application name as shown in Runtime Manager. | |
| endTime | No | Application Manager time filter, ISO 8601. | |
| errorOnly | No | Only return ERROR and FATAL lines. | |
| startTime | No | Application Manager time filter, ISO 8601. | |
| descending | No | Return latest first, default true. | |
| includeRaw | No | Include the raw Anypoint API objects alongside the normalized fields. | |
| searchTerms | No | Case-insensitive filters matched against timestamp, priority, message, logger, thread or instance. | |
| deploymentId | No | Use when the app name is ambiguous or already known. | |
| environmentId | No | Environment id. Use instead of environmentName. | |
| includeErrors | No | Include failed target errors when target is auto. | |
| environmentName | No | Environment name, e.g. 'Production'. Resolved to an id, must match exactly one. |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden, and it does disclose meaningful traits: the logs are live-tail (not archived, implying ephemeral/non-historical data) and the response is an analysis-ready aggregate rather than raw entries. It still omits the read-only safety profile, permission requirements, and any latency or streaming caveats around live-tail fetching.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences with zero filler; the capability and payload shape come first, then the routing preference. Nothing is repeated from the schema and every clause earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema, the description usefully characterizes the return payload, and the rich parameter schema covers input details. It is nearly complete for a read tool of this complexity, though pagination/offset behavior on a live-tail stream and failure modes when no target is reachable are left unstated.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% across 16 parameters, including defaults, ranges and enum values, so the schema already documents parameter meaning thoroughly. The description adds only indirect context (the priority/logger/instance fields that searchTerms match against), so the baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource ('Fetch live-tail logs for a Mule application') and goes further by naming the shape of the returned payload (normalized lines plus counts by priority, logger and instance). It explicitly distinguishes itself from the sibling anypoint_list_app_logs, so an agent can route without opening either schema.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives a clear selection rule: 'Prefer this over anypoint_list_app_logs when diagnosing a problem.' It names the alternative and the condition that favors this tool. It stops short of stating when the sibling is the better choice (e.g., raw paginated log listing), so it is not fully bidirectional guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
anypoint_list_api_manager_instancesList API Manager instancesB
List API instances managed by Anypoint API Manager in an environment, with their assets, endpoints and technology.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum records, default 100. | |
| orgId | No | Business group id. Defaults to ANYPOINT_ORG_ID, or the credentials' own organization. | |
| offset | No | Pagination offset, default 0. | |
| assetId | No | Filter by Exchange asset id. | |
| includeRaw | No | Include the raw Anypoint API objects alongside the normalized fields. | |
| technology | No | Filter by technology, e.g. mule4, flexGateway. | |
| environmentId | No | Environment id. Use instead of environmentName. | |
| environmentName | No | Environment name, e.g. 'Production'. Resolved to an id, must match exactly one. |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are supplied, so the description carries the full behavioral burden. It usefully discloses what comes back (assets, endpoints, technology) and, via the includeRaw parameter, that normalized fields are the default. However, it says nothing about pagination semantics, permission/credential requirements, or rate limits for what is implicitly a read-only list operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single front-loaded sentence that names the operation, the scope, and the return payload with no filler or redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a read-only list tool with no annotations and no output schema, the description does the essential work of stating what is listed and roughly what is returned. It is nearly complete; pagination and environment-selection nuance are covered by the rich schema, so only minor context is missing.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents all eight parameters including defaults, filtering, and the environmentId/environmentName exclusivity. The description adds nothing about parameter behavior, so the baseline of 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb (List) and a precisely bounded resource (API instances managed by Anypoint API Manager), plus the scope (an environment) and the payload returned (assets, endpoints, technology). It is naturally distinct from siblings like anypoint_list_deployed_apps and anypoint_list_environments, though it never explicitly contrasts itself with them.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The phrase 'in an environment' hints that environment scoping matters, but there is no explicit when-to-use guidance, no prerequisites, and no mention of when a caller should reach for this tool versus anypoint_list_deployed_apps or anypoint_search_exchange_assets. An agent gets no routing help from the text.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
anypoint_list_app_logsList application logsA
List the latest Runtime Manager logs for a Mule application. This reads the live tail only — a small rolling buffer. For anything older than the buffer, use anypoint_search_archived_logs.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum log entries, default 100, max 500. | |
| orgId | No | Business group id. Defaults to ANYPOINT_ORG_ID, or the credentials' own organization. | |
| offset | No | Application Manager log offset, default 0. | |
| specId | No | Specific Application Manager deployment spec/config id. | |
| target | No | Log source. Defaults to auto, which tries Application Manager then CloudHub. | |
| appName | Yes | Deployment/application name as shown in Runtime Manager. | |
| endTime | No | Application Manager time filter, ISO 8601. | |
| startTime | No | Application Manager time filter, ISO 8601. | |
| descending | No | Return latest first, default true. | |
| includeRaw | No | Include the raw Anypoint API objects alongside the normalized fields. | |
| deploymentId | No | Use when the app name is ambiguous or already known. | |
| environmentId | No | Environment id. Use instead of environmentName. | |
| includeErrors | No | Include failed target errors when target is auto. | |
| environmentName | No | Environment name, e.g. 'Production'. Resolved to an id, must match exactly one. |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden, and it does disclose the most consequential behavioral trait: results come from a bounded rolling buffer rather than full history. It omits other traits the agent would want — read-only nature (only implied by 'List'), rate/volume limits, and how the 'auto' target fallback behaves — but the buffer caveat is the key gotcha and it is stated plainly.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences with zero filler; the scope limitation is front-loaded and the alternative is appended as the resolution. Nothing redundant with the name or title.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a 14-parameter tool with no annotations and no output schema, the description covers the essential conceptual gap (live tail vs. archive) but says nothing about output shape, pagination across offset/limit, or the behavior of the auto target fallback and includeErrors flag. Adequate, though an agent still infers a fair amount from the schema alone.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% across all 14 parameters, so the schema already explains limit, offset, target, time filters, environment resolution, and the rest. The description adds no parameter-level detail beyond what the schema provides, which is the expected baseline when the schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource ('List the latest Runtime Manager logs for a Mule application') and immediately bounds what 'logs' means here. It also names the sibling it is not (anypoint_search_archived_logs), so an agent can distinguish it from anypoint_get_app_logs_for_analysis and the archived-log tool without opening schemas.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly defines the operating window ('live tail only — a small rolling buffer') and states the exclusion condition plus the named alternative: 'For anything older than the buffer, use anypoint_search_archived_logs.' That is a direct when-to-use/when-not-to-use routing rule.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
anypoint_list_business_groupsList business groupsA
List the business groups under the credentials' organization, with their ids. Environments live on business groups, not on the root organization — call this first if anypoint_list_environments returns nothing.
| Name | Required | Description | Default |
|---|---|---|---|
| rootOrgId | No | Root organization id. Defaults to the credentials' own organization. |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It does disclose a meaningful domain behavior (environments live on business groups, not the root organization) and that ids are returned, but it says nothing about auth/permission requirements, pagination, or the size/shape of the result set.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two tightly written sentences with zero filler; the core purpose comes first and the fallback routing follows. Every clause earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a single-optional-param, annotation-free read tool with no output schema, the description covers purpose, scope, defaulting behavior, and cross-tool routing. Remaining gaps (result size, pagination, permission needs) are minor given the tool's simplicity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% and there is only one optional parameter (rootOrgId), whose default behavior is already documented in the schema. The description adds no syntax or format detail beyond the schema, so the 3 baseline applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb+resource ('List the business groups') and scope ('under the credentials' organization'), plus notes the returned ids. It also implicitly separates itself from anypoint_list_environments by explaining that environments hang off business groups rather than the root org.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Gives an explicit conditional directive: 'call this first if anypoint_list_environments returns nothing,' naming the sibling tool and the failure condition that should route the agent here. This is exactly the when/when-alternative guidance the dimension asks for.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
anypoint_list_deployed_appsList deployed applicationsB
List deployed Mule applications in an environment, across Application Manager (CloudHub 2.0 / Runtime Fabric), legacy CloudHub, and hybrid on-prem targets.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum records to return, default 100. | |
| orgId | No | Business group id. Defaults to ANYPOINT_ORG_ID, or the credentials' own organization. | |
| target | No | Deployment target to query. Defaults to application_manager. | |
| includeRaw | No | Include the raw Anypoint API objects alongside the normalized fields. | |
| environmentId | No | Environment id. Use instead of environmentName. | |
| includeErrors | No | Include per-target errors when a target endpoint is unavailable or not permitted. | |
| environmentName | No | Environment name, e.g. 'Production'. Resolved to an id, must match exactly one. |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It usefully discloses that the tool federates across Application Manager, legacy CloudHub, and hybrid targets, which is real behavioral context not available in the schema, but it is silent on read-only nature, permission requirements, and empty-result behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single front-loaded sentence that names the resource first and then qualifies scope; every clause carries information and there is no filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a 7-parameter list tool with no output schema and full schema coverage, the description is nearly complete. The only gap is the absence of any hint about the shape of the normalized results, which the schema cannot supply.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so every parameter (limit, target, orgId, environmentId/environmentName, includeRaw, includeErrors) is already documented. The description echoes the environment scoping and target variety but adds no syntax or precedence detail beyond the schema's baseline.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb (List) and resource (deployed Mule applications), and scopes them to an environment across three target families. It does not name or contrast any sibling tool, so an agent must infer how it differs from anypoint_list_app_logs or anypoint_list_environments.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no when-to-use guidance, no exclusions, and no alternative tools mentioned. The phrase 'in an environment' hints that an environment parameter is expected, but the description never states the condition that selects this tool over its siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
anypoint_list_environmentsList environmentsA
List the Anypoint environments in a business group. If this returns nothing, the orgId is probably the root organization — call anypoint_list_business_groups to find the right id. Restricted to ANYPOINT_ALLOWED_ENVIRONMENTS when that is set.
| Name | Required | Description | Default |
|---|---|---|---|
| orgId | No | Business group id. Defaults to ANYPOINT_ORG_ID, or the credentials' own organization. |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description carries the full disclosure burden, and it does add real behavior: output may be filtered by the ANYPOINT_ALLOWED_ENVIRONMENTS setting, and an empty result has a specific diagnostic meaning (root org) rather than 'no data'. It still omits pagination and permission/auth requirements, so it is not exhaustive.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three tight sentences, front-loaded with the core action, followed by the empty-result remedy and the filtering caveat. No filler and nothing redundant.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a single optional-parameter list tool with no output schema, the description covers the action, the result caveat, the fallback path, and the filtering constraint. An agent has everything needed to call it correctly and interpret an empty response.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, and the schema already documents the orgId default chain (ANYPOINT_ORG_ID, then credentials' organization). The description only echoes the 'business group' framing and adds the root-org troubleshooting hint, so it does not meaningfully extend parameter meaning beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource with scope: 'List the Anypoint environments in a business group.' That is concrete enough for an agent to act on immediately. It does not explicitly contrast itself with the sibling listing tools, though it does route to anypoint_list_business_groups for a specific failure mode.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Gives an explicit conditional path: if the call returns nothing, the orgId is likely the root organization and the agent should call anypoint_list_business_groups instead. It also flags that results are restricted when ANYPOINT_ALLOWED_ENVIRONMENTS is set, which tells the agent when a partial list is expected rather than a bug.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
anypoint_search_archived_logsSearch archived logsA
Search historical Mule application logs via the Anypoint Monitoring Archive API, for dates beyond the live tail's rolling buffer. Requires Anypoint Monitoring to be enabled for the organization. Use this for any past-date incident investigation.
| Name | Required | Description | Default |
|---|---|---|---|
| date | Yes | Required date to search, YYYY-MM-DD (UTC). | |
| limit | No | Cap on matched lines returned, default 500. | |
| orgId | No | Business group id. Defaults to ANYPOINT_ORG_ID, or the credentials' own organization. | |
| appName | Yes | Deployment name, must match the Runtime Manager name exactly. | |
| endDate | No | Inclusive range end, YYYY-MM-DD (UTC). Max 7 days total. | |
| maxFiles | No | Cap on archive files downloaded and parsed, default 100. | |
| errorOnly | No | Only return ERROR and FATAL lines. | |
| includeRaw | No | Include the raw Anypoint API objects alongside the normalized fields. | |
| maxEntities | No | Cap on replica entities probed during a full-scan fallback, default 150. | |
| searchTerms | No | Case-insensitive text filters. | |
| environmentId | No | Environment id. Use instead of environmentName. | |
| environmentName | No | Environment name, e.g. 'Production'. Resolved to an id, must match exactly one. |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It usefully discloses the enabling prerequisite, but says nothing about read-only nature, authorization failures when Monitoring is disabled, throttling, or the archive-file download/parse cost implied by maxFiles/maxEntities. Prerequisite disclosure is real added value, but the behavioral picture is incomplete.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three sentences with no filler; the API/purpose leads, the prerequisite follows, and the use case closes. Nothing is repeated from the schema.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a 12-parameter tool with no output schema and no annotations, the description covers purpose, scope boundary, prerequisite, and intended use case adequately. It could do slightly more on fallback behavior (full-scan replica probing) and return shape, but the essential calling context is present.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% and every parameter (date range, limit, maxFiles, maxEntities, errorOnly, environment resolution) is already documented in the schema. The description adds no parameter-level meaning beyond it, so the baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb (search) and resource (historical Mule application logs) and names the underlying API. It also distinguishes itself from sibling log tools by scope ('dates beyond the live tail's rolling buffer'), so an agent can separate it from anypoint_list_app_logs without opening a schema.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Gives clear context ('for dates beyond the live tail's rolling buffer', 'past-date incident investigation') and states a prerequisite (Anypoint Monitoring enabled). It doesn't explicitly name the sibling to use for live/near-real-time logs, leaving that routing to inference, which keeps it short of a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
anypoint_search_exchange_assetsSearch Exchange assetsC
Search Anypoint Exchange for assets in the organization — APIs, connectors, templates, examples and fragments.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum records, default 50. | |
| orgId | No | Business group id. Defaults to ANYPOINT_ORG_ID, or the credentials' own organization. | |
| types | No | Filter by asset type, e.g. rest-api, connector, template, example. | |
| offset | No | Pagination offset, default 0. | |
| search | No | Free-text search over asset names and descriptions. | |
| includeRaw | No | Include the raw Anypoint API objects alongside the normalized fields. |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure, and it says nothing about read-only safety, authentication/organization scoping, or rate limits. It also adds no return-shape or pagination behavior beyond what the schema already documents for limit/offset. The implicit read-only nature of 'search' is the only signal.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single efficient sentence with the verb and resource front-loaded and the covered asset types listed as a scannable clause. Nothing is wasted, though the sentence is short enough that it leaves obvious gaps unfilled rather than being maximally informative.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With six optional parameters, 100% schema coverage, and no output schema, the description is adequate but minimal. It does not describe what the returned assets look like or how search interacts with the types filter, so an agent gets no help on result interpretation beyond the schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so all six parameters are already documented in the schema (limit, orgId, types, offset, search, includeRaw). The description reinforces the types filter by naming asset kinds, but adds no format or syntax detail beyond the schema. Baseline 3 applies when the schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description gives a specific verb (Search) and resource (Anypoint Exchange assets), and enumerates the asset kinds covered (APIs, connectors, templates, examples, fragments). It is instantly distinguishable from the sibling tools, which all target different resources (environments, apps, logs, business groups). No explicit sibling routing is needed because none of them overlap.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no explicit when-to-use guidance, no prerequisites, and no mention of alternatives or when not to use it. That you would call it to find assets is only implied by the verb. For a search tool this leaves the agent to infer scoping and pagination strategy on its own.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
anypoint_whoamiCheck Anypoint connectionA
Verify the configured Anypoint credentials and show which business group, host and environment allowlist this server is operating with. Use this first when a call fails.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden, and it does distinguish itself as a verification/inspection read rather than a mutation and frames itself as a troubleshooting entry point. It omits whether verification fails hard on bad credentials and what the output looks like, which is a minor gap given zero parameters.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two tightly written sentences with no filler. The identity/verification purpose comes first and the troubleshooting cue is placed last as the actionable instruction.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Although there is no output schema, the description enumerates the fields it surfaces (business group, host, environment allowlist), which is enough for an agent to know what it gets back. Only the failure semantics of a bad-credential check are unstated.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool takes no parameters, so there is nothing to disambiguate; baseline is 4. The description correctly indicates the results are derived from server-side configuration rather than caller-supplied input.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description pairs specific verbs (verify, show) with concrete resources (Anypoint credentials, business group, host, environment allowlist), going well beyond the name 'whoami'. It is clearly a diagnostic/identity tool, which cleanly separates it from the list_* siblings.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It gives an explicit triggering condition: 'Use this first when a call fails.' That is real when-to-use guidance. It stops short of naming alternatives or stating when not to use it, but no sibling serves the same diagnostic purpose.
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.
9 tool updates
v0.1.1- First observed
anypoint_get_app_logs_for_analysis - First observed
anypoint_list_api_manager_instances - First observed
anypoint_list_app_logs - First observed
anypoint_list_business_groups - First observed
anypoint_list_deployed_apps - First observed
anypoint_list_environments - First observed
anypoint_search_archived_logs - First observed
anypoint_search_exchange_assets - First observed
anypoint_whoami
TDQS
Scored across 9 tools
Most tools target a clearly distinct resource (environments, business groups, deployed apps, API instances, exchange assets). The only real overlap is anypoint_list_app_logs vs anypoint_get_app_logs_for_analysis, which both read the live tail, but the descriptions explicitly differentiate them and recommend the analysis variant for diagnosis.
All nine tools follow a strict anypoint_verb_noun pattern (list_environments, get_app_logs_for_analysis, search_archived_logs, etc.). The prefix is uniform and verb choice (list/get/search) is used predictably.
Nine tools is well within the sweet spot for an observability/management server. Each tool maps to a distinct Anypoint concern (org topology, apps, logs, API manager, exchange) so nothing feels padded.
The surface covers topology discovery, app listing, live and archived logs, API instances, and Exchange assets — a solid monitoring story. Minor gaps remain: no single-app detail/health/metrics lookup and only list-style access for apps, but agents can work around these with the existing calls.
Maintenance
Related MCP Connectors
Query your org's data in natural language — read-only MCP access to SQL, NoSQL, files & warehouses.
Read-only access to Auralogs production logs: search logs, inspect errors, review AI analyses.
Read-only MCP access to a documented IT fleet: state, changes, posture. 15 tools.
Access New Relic observability data through MCP - query metrics, logs, traces, entities, and more
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables natural-language investigation of Datadog data including logs, metrics, monitors, traces, hosts, dashboards, events, and incidents, all through read-only API access.2,145 npmMIT
- AlicenseNot gradedqualityCmaintenanceProvides read-only access to Loki, Prometheus, and Tempo APIs, enabling natural language queries for logs, metrics, and traces. Supports multiple instances and authentication via bearer tokens.1MIT
- AlicenseAqualityBmaintenanceEnables natural-language queries about Azure resource compliance, including VM compliance, patch status, orphaned RBAC, and infrastructure health, through read-only MCP tools.3MIT
- FlicenseNot gradedqualityCmaintenanceLets you inspect the health of your AWS Lambda functions and S3 buckets using plain English, with read-only access.-