Testing Bank MCP
Offers tools to test the PagerDuty-Jira integration, including creating test incidents and verifying automatic Jira ticket creation.
Provides tools for managing PagerDuty services, creating test incidents, listing extensions/webhooks, and diagnosing integration issues with connected services.
Enables testing of the PagerDuty-Salesforce integration with tools for creating test incidents and diagnosing synchronization issues.
Provides capabilities to test the PagerDuty-Slack integration, such as sending test messages to Slack channels and verifying webhook configurations.
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., "@Testing Bank MCPPD incidents not appearing in Teams"
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.
Testing Bank MCP
A Model Context Protocol (MCP) router that connects to multiple PagerDuty sandbox environments for testing integrations.
Architecture
┌─────────────────────────────────┐
│ Testing Bank Router MCP │
│ (Orchestrator/Gateway) │
└───────────────┬─────────────────┘
│
┌───────────┼───────────┐
│ │ │
▼ ▼ ▼
┌────────┐ ┌────────┐ ┌────────┐
│PD+Teams│ │PD+Jira │ │PD+Slack│ ... more environments
└────────┘ └────────┘ └────────┘Related MCP server: pagerduty-mcp-community
Available Environments
Environment | Description |
| PagerDuty + Microsoft Teams |
| PagerDuty + Jira Cloud |
| PagerDuty + Salesforce |
| PagerDuty + Slack |
| PagerDuty + AWS CloudWatch/EventBridge |
Installation
cd testing-bank-mcp
npm installConfiguration
1. Set up environment files
Copy the example files and fill in your sandbox credentials:
# For PD + Teams
cp environments/pd-teams/.env.example environments/pd-teams/.env
# For PD + Jira
cp environments/pd-jira/.env.example environments/pd-jira/.env2. Configure your MCP client
Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"testing-bank": {
"command": "node",
"args": ["router/index.js"],
"cwd": "/full/path/to/testing-bank-mcp"
}
}
}Usage
Smart Routing (Recommended)
Just describe the customer issue and the router will detect the right environment:
"Customer reports PagerDuty incidents are not posting to their Teams channel"The router will:
Detect this is a PD + Teams issue
Connect to the
pd-teamsenvironmentGive you access to all PD and Teams testing tools
Manual Environment Selection
1. List available environments: list_environments
2. Connect to specific environment: connect_environment("pd-jira")
3. Use environment tools: route_to_environment("pd-jira", "diagnose_integration")Router Tools
Tool | Description |
| List all available testing environments |
| Auto-detect environment from issue description |
| Connect to a specific environment |
| Disconnect from an environment |
| List currently connected environments |
| Send commands to a connected environment |
| Auto-detect and connect in one step |
Environment Tools (PD + Teams Example)
Tool | Description |
| List PagerDuty services |
| Create test incident |
| List webhooks/integrations |
| Send test message to Teams |
| Verify webhook configuration |
| Run full end-to-end test |
| Diagnose common issues |
Example Workflow
User: "Customer says PD incidents aren't creating Jira tickets"
AI uses: smart_route("PD incidents aren't creating Jira tickets")
→ Detects: pd-jira environment
→ Connects to PD + Jira sandbox
AI uses: diagnose_integration()
→ Checks PD API connection
→ Checks Jira API connection
→ Lists Jira extensions in PD
→ Returns recommendations
AI uses: test_full_integration(service_id="PXXXXXX")
→ Creates test incident in PD
→ Waits for Jira sync
→ Searches for created ticket
→ Reports resultsAdding New Environments
Create directory:
environments/pd-newservice/Copy template from existing environment
Modify API calls for the new service
Add environment to
ENVIRONMENTSinrouter/index.jsCreate
.env.examplewith required credentials
Security Notes
Never commit
.envfilesUse sandbox/test environments only
Rotate API keys regularly
Document which sandboxes are connected to production data (if any)
Available Tools
7 toolsconnect_environmentC
Connect to a specific testing environment sandbox
| Name | Required | Description | Default |
|---|---|---|---|
| environment_id | Yes | The environment ID to connect to (e.g., 'pd-teams', 'pd-jira', 'pd-salesforce') |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must bear the full burden of behavioral disclosure. It only states 'Connect to a specific testing environment sandbox' without explaining side effects (e.g., state changes, authentication requirements, or whether a prior connection is terminated). This is insufficient for an agent to predict the tool's impact.
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?
The description is concise at one sentence and front-loads the key action. However, it lacks structure such as bullet points or separate sections. Every sentence earns its place, but more detail could be added without becoming verbose.
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?
Given the lack of output schema and the simplicity of the input, the description is too sparse. It does not explain what happens after connection, prerequisites, or return behavior. For a tool that likely has side effects (e.g., establishing a session), this is incomplete.
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 single parameter `environment_id` has 100% schema coverage with a clear enum and description. The description adds no additional meaning beyond what the schema already provides. A baseline of 3 is appropriate since the schema is self-sufficient.
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 clearly states the action ('Connect') and the resource ('specific testing environment sandbox'). However, it does not differentiate from sibling tools like 'route_to_environment' or 'detect_environment', which could have overlapping meaning. A more precise description would clarify what 'connect' entails uniquely.
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?
No guidance is provided on when to use this tool versus alternatives. The sibling tools include 'disconnect_environment', 'route_to_environment', etc., but the description does not help the agent choose between them. Explicit context for when to connect versus route or detect is missing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
detect_environmentB
Automatically detect which environment to use based on a customer issue description
| Name | Required | Description | Default |
|---|---|---|---|
| issue_description | Yes | Description of the customer issue (e.g., 'PagerDuty incidents not posting to Teams channel') |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so the description must disclose behavioral traits. It only states 'detect' without explaining if the tool modifies state, returns a selection, or requires any prerequisites.
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?
Single sentence, no redundancy. Could be slightly expanded for clarity but remains efficient.
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?
Without output schema or behavioral details, the description is incomplete. A simple tool with one parameter still needs to explain what 'detect' means and what the agent can expect.
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% with a clear description of 'issue_description'. The tool description adds no extra meaning, so baseline score of 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?
The description clearly states the action ('detect') and the resource ('environment'), and specifies the input ('customer issue description'). It distinguishes from sibling tools like connect_environment or smart_route.
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?
No guidance on when to use this tool versus alternatives like route_to_environment or smart_route. The description implies usage for automatic detection but does not specify exclusion criteria.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
disconnect_environmentB
Disconnect from a testing environment
| Name | Required | Description | Default |
|---|---|---|---|
| environment_id | Yes | The environment ID to disconnect from |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description does not disclose behavioral traits beyond the basic action. It does not mention whether disconnection is reversible, what side effects occur, or any authentication requirements.
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?
The description is a single, concise sentence that efficiently conveys the tool's purpose. It is front-loaded and contains no unnecessary words.
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 simple tool with one parameter and no output schema, the description is adequate but lacks context such as prerequisites (e.g., being connected first) or post-conditions.
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 schema covers 100% of parameters, including an enum and description for 'environment_id'. The description adds no additional meaning beyond what the schema provides, so 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?
The description clearly states the action ('disconnect') and the resource ('testing environment'). It distinguishes itself from siblings like 'connect_environment' by naming the opposite operation.
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?
No guidance is provided on when to use this tool versus its siblings (e.g., 'connect_environment', 'detect_environment'). The description lacks context about prerequisites or alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_active_environmentsB
Get list of currently connected environments
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description indicates a read operation without side effects, which is accurate for a simple listing. However, with no annotations, it does not explicitly state non-destructiveness or other behavioral traits beyond the implied read.
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?
Single sentence, perfectly sized for a tool with no parameters and straightforward purpose. No wasted words.
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?
While low complexity, the description lacks details on the return format (e.g., properties of environment objects). Without an output schema, the agent is left guessing about the response structure.
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?
No parameters exist, so schema coverage is 100%. Description does not need to add parameter info; baseline for zero parameters is 4.
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 clearly states the tool gets a list of currently connected environments. It differentiates from sibling 'list_environments' implicitly by specifying 'active', but does not explicitly contrast 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?
No guidance on when to use this tool versus alternatives. With siblings like 'list_environments', the description fails to clarify the distinction or provide context for selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
list_environmentsA
List all available testing environments in the Testing Bank
| 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 offers minimal behavioral context beyond 'list'. It does not disclose any potential side effects, authentication requirements, or output format.
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?
The description is a single, clear sentence with no unnecessary words. It is front-loaded and efficient.
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?
Given the tool's simplicity (zero parameters, no nested objects, no output schema), the description is nearly complete. It could briefly mention what information is returned but overall adequate.
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 has zero parameters; the baseline score of 4 applies per guidelines. The description does not need to add parameter information.
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 clearly states the verb 'list' and the resource 'all available testing environments'. It is distinguishable from siblings like get_active_environments, which lists only active ones.
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 implies that this tool is for listing all available environments but does not explicitly state when to use it versus alternatives like get_active_environments or connect_environment.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
route_to_environmentB
Send a command to a connected environment. Use this to execute tools in the child environment.
| Name | Required | Description | Default |
|---|---|---|---|
| tool_args | No | Arguments to pass to the tool | |
| tool_name | Yes | The tool name to execute in the environment | |
| environment_id | Yes | The environment ID to route to |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description bears full responsibility for behavioral disclosure. It states 'Send a command to a connected environment' but does not specify what happens if the environment is not connected, if the tool name is invalid, or if there are side effects (e.g., state changes, rate limits). The description is too sparse to offer meaningful behavioral transparency.
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?
The description is extremely concise: two sentences with no fluff or repetition. Every word is functional. It is front-loaded with the verb 'Send' and the key object 'command'. This is an appropriate length for a simple routing tool.
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?
The tool has 3 parameters, one of which is a nested object (tool_args) that could have complex structure. No output schema is provided. The description does not explain what the command returns, how errors are reported, or any prerequisites (e.g., environment must be active). Given the complexity of routing and possible failure modes, the description is incomplete.
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?
Input schema covers all 3 parameters with descriptions (100% coverage). The description adds no additional meaning beyond the schema. For high coverage, baseline is 3, and the description does not compensate with extra context.
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 'Send a command to a connected environment. Use this to execute tools in the child environment.' clearly states the action (send a command) and the target (connected environment). It distinguishes from sibling tools like connect_environment or list_environments which deal with lifecycle and discovery, not execution. However, it doesn't explicitly mention that the environment must already be connected or that the tool must be a known tool in that environment, leaving some ambiguity.
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 provides basic guidance: 'Use this to execute tools in the child environment.' This implies the tool is intended for running tools in a specific environment. However, no when-not-to-use advice is given, and no distinction from 'smart_route' is provided. A sibling tool named 'smart_route' might be an alternative, but the description doesn't clarify when each is appropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
smart_routeA
Automatically detect the right environment from issue description and connect to it
| Name | Required | Description | Default |
|---|---|---|---|
| issue_description | Yes | Description of the customer issue |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description bears full responsibility. It discloses that the tool both detects and connects (a mutation), but lacks details on failure modes, permissions required, or what happens if detection fails. The disclosure is adequate but not rich.
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?
The description is a single, concise sentence of 12 words with no wasted words. It is front-loaded with the action and resource.
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?
Given the simple tool with one parameter and no output schema or annotations, the description covers the main use case. However, it lacks information about edge cases (e.g., multiple environment matches, detection failure) and does not clarify how this tool differs from route_to_environment. Still, it is mostly complete for its 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?
The only parameter, issue_description, is described in the schema as 'Description of the customer issue.' The tool description adds that it is used to 'automatically detect the right environment,' which provides context beyond the schema. With 100% schema coverage, baseline is 3, and the description adds value, so a 4 is warranted.
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 clearly states that the tool detects the right environment from an issue description and connects to it, using specific verbs (detect and connect) and a specific resource (environment). This distinguishes it from sibling tools like connect_environment (which just connects) and detect_environment (which just detects).
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 implies that this tool should be used when the environment is unknown and needs to be inferred from the issue, but it does not explicitly state when not to use it or provide alternatives. With siblings like connect_environment and detect_environment, explicit guidance would be beneficial.
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.
7 tool updates
v1.0.0- First observed
connect_environment - First observed
detect_environment - First observed
disconnect_environment - First observed
get_active_environments - First observed
list_environments - First observed
route_to_environment - First observed
smart_route
TDQS
Tools are mostly distinct, but detect_environment and smart_route have overlapping purposes (detecting vs detecting+connecting), which could cause some confusion. Other tools clearly cover different actions.
Six tools follow verb_noun snake_case pattern (e.g., connect_environment, list_environments). smart_route deviates by starting with an adjective instead of a verb, breaking the pattern slightly.
With 7 tools, the set is well-scoped for managing testing environments: connect, detect, disconnect, list, route, and smart route cover essential operations without bloat.
The tool surface covers core lifecycle (connect, disconnect, list, interact) and adds detection features. Missing environment creation or modification, but those may be out of scope for a testing bank server.
Maintenance
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
MCP server for building and testing AI agents with multi-model experimentation and insights.
Connect MCP clients to 2,000+ AI models without managing provider API keys.
- GentkeyOAuthcom.gentkey
One MCP URL for all your connectors — scoped writes, enforced constraints, and a full audit trail.
One MCP endpoint for Claude, GPT & Gemini: 100+ tools + no-code connectors + agent workers.
Related MCP Servers
- AlicenseNot gradedqualityAmaintenanceA unified hub for centrally managing and dynamically orchestrating multiple MCP servers/APIs into separate endpoints with flexible routing strategies.7162,371Apache 2.0
- AlicenseAqualityCmaintenanceA community-maintained MCP server for interacting with PagerDuty accounts, enabling management of incidents, services, schedules, and event orchestrations through MCP-enabled clients.201Apache 2.0

pagerduty-mcpofficial
AlicenseBqualityFmaintenanceEnables management of PagerDuty incidents, services, schedules, and more directly from MCP-enabled clients, with embedded interactive UIs for incident command center, on-call management, and other features.6377Apache 2.0- AlicenseBqualityCmaintenanceUnified MCP server for DevOps engineers that provides real-time read and write access to Kubernetes, ArgoCD, Prometheus, and PagerDuty from any MCP-compatible AI agent.211492MIT
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/RFH-PDTest/testing-bank-router-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server