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., "@mcp-counter-server parse counter tags from my analysis output"
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.
A Model Context Protocol (MCP) server that provides stateful counter tools for AI assistants. This solves the problem of AI's inability to reliably count items during iteration by providing explicit, accurate counter tools.
AI language models use probabilistic pattern matching rather than actual counting. This makes them unreliable for tasks like:
Tracking how many files have been processed
Counting iterations in a loop
Maintaining progress through multi-step tasks
Accurately tallying errors, warnings, or other metrics
Related MCP server: text-count-mcp-server
This MCP server provides explicit counter tools that maintain accurate state. AI assistants can:
Embed counter tags directly in their output as they work
Process all tags in one call with counter_parse_and_apply
Track multiple metrics simultaneously with perfect accuracy
Review history to see every operation performed
git clone https://github.com/Discordit142/mcp-counter-server.git
cd mcp-counter-server
npm install
npm run buildAdd this to your VS Code User Settings (Ctrl+, → search "MCP" → Edit in settings.json):
{
"mcp.servers": {
"counter": {
"type": "stdio",
"command": "node",
"args": ["<path-to-repo>/dist/index.js"]
}
}
}Replace <path-to-repo> with the actual path to your cloned repository.
Embed counter tags directly in your text as you work, then process them all at once:
Processing files in workspace...
Analyzing src/index.ts [+1:files_analyzed]
- Found 15 async functions [+15:async_functions]
- Found 2 interface definitions [+2:interfaces]
- Detected 3 minor issues [+3:warnings]
Analyzing package.json [+1:files_analyzed]
- Configuration validated
Analyzing README.md [+1:files_analyzed]
- Documentation complete
Analysis finished!Then call counter_parse_and_apply with the entire text above, and get:
{
"counters": {
"files_analyzed": 3,
"async_functions": 15,
"interfaces": 2,
"warnings": 3
},
"errors": []
}Shorthand (explicit numbers required):
[+N:counter_id] - Increment by N
[-N:counter_id] - Decrement by N
[reset:counter_id] - Reset to 0
[delete:counter_id] - Delete counter
[set:N:counter_id] - Set to specific value
Full Syntax (alternative):
[-counter:counter_id:+N-] or [-c:counter_id:+N-] - Increment/decrement
[-counter:counter_id:reset-] - Reset
[-counter:counter_id:delete-] - Delete
[-counter:counter_id:set:N-] - Set value
Examples:
[+1:files] → files: 1
[+15:lines_of_code] → lines_of_code: 15
[-3:errors] → errors: -3
[reset:temp] → temp: 0
[set:100:progress] → progress: 100
[delete:old_counter] → (counter removed)For simple cases, call counter tools directly:
counter_increment(counter_id: "files_processed")
counter_increment(counter_id: "errors_found", amount: 5)
counter_get(counter_id: "files_processed") // Returns current value
counter_reset(counter_id: "errors_found") // Reset to 0
counter_delete(counter_id: "temp_counter") // Remove completelycounter_parse_and_applyParse counter tags from text and execute all operations in order.
Arguments:
text (required): Text containing counter tags
debug (optional): Enable debug mode for detailed results (default: false)
Streamlined Mode (default):
{
"counters": { "files": 5, "errors": 2 },
"errors": []
}Debug Mode:
{
"counters": { "files": 5 },
"errors": [],
"processed_tags": [
{ "tag": "[+1:files]", "result": "files incremented by 1" },
{ "tag": "[+4:files]", "result": "files incremented by 4" }
]
}counter_incrementIncrement a counter by a specified amount (creates if doesn't exist).
Arguments:
counter_id (required): Unique identifier
amount (optional): Amount to increment (default: 1, can be negative)
counter_getGet current value and metadata for a counter.
Arguments:
counter_id (required): Counter to retrieve
counter_resetReset a counter to 0 (preserves history).
Arguments:
counter_id (required): Counter to reset
counter_listList all active counters with their current values.
counter_historyGet operation history for a counter.
Arguments:
counter_id (required): Counter to retrieve history for
limit (optional): Max number of recent entries
counter_deletePermanently delete a counter and its history.
Arguments:
counter_id (required): Counter to delete
Starting database migration...
Connecting to database... [+1:steps_completed]
Backing up existing data... [+1:steps_completed]
Processing 1000 records:
Record batch 1-100: [+100:records_processed] [+2:errors_found]
Record batch 101-200: [+100:records_processed] [+1:errors_found]
Record batch 201-1000: [+800:records_processed]
Migration complete!
Setting total records: [set:1000:total_records]
Final status:
- Steps completed: (will show 2)
- Records processed: (will show 1000)
- Errors found: (will show 3)Pass this text to counter_parse_and_apply and get accurate counts instantly.
✅ Accurate counting - No probabilistic approximation
✅ Batch processing - Process hundreds of tags in one call
✅ History tracking - Every operation logged with timestamp
✅ Multiple counters - Track different metrics simultaneously
✅ Persistent within session - Counters survive across tool calls
✅ Flexible operations - Increment, decrement, set, reset, delete
✅ Error handling - Continues processing even if individual tags fail
✅ Race-condition safe - Per-counter locking prevents conflicts
npm run build # Compile TypeScript
npm run watch # Watch mode for development
npm run dev # Run with Node inspector
npm start # Run the compiled serverCounterStore: In-memory store with per-counter locking
Counter: Data structure with id, value, history, timestamps
parseAndApplyTags: Regex-based tag extraction and processing
MCP Server: Exposes tools via Model Context Protocol
Multi-file analysis (track files, functions, classes found)
Long-running operations (track progress, errors, warnings)
Batch processing (accurately count processed items)
Quality metrics (track code quality scores across multiple files)
Agent workflows (multiple agents incrementing shared counters)
Preserving calculations past context compression: Store important calculation results as named counters (e.g., [set:15:error_rate_percentage]) to survive conversation summarization. AI assistants can retrieve these values later even after context is compressed.
MIT License - see LICENSE file for details
Issues and pull requests welcome at github.com/Discordit142/mcp-counter-server
Permanently delete a counter and all its history.
| Name | Required | Description | Default |
|---|---|---|---|
| counter_id | Yes | Unique identifier for the counter |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations are absent, so the description bears full responsibility for disclosure. It clearly communicates the irreversible destructive nature ('permanently delete') and the fact that historical data is included. However, it does not address error scenarios, permission requirements, or post-deletion behavior, which could be useful.
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, front-loaded sentence that efficiently conveys the essential behavior without any extraneous words. Every word 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 simple delete tool with one parameter and no output schema, the description is functionally complete: it names the resource, the permanence, and the historical scope. It does not describe return values or edge cases, but these are less critical for a destructive action with minimal schema complexity.
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 input schema already provides 100% coverage for the single parameter counter_id with a clear description. The tool 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.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: to permanently delete a counter and all its history. The verb 'delete' is specific, the resource is a counter, and the scope (all history) is explicit, distinguishing it from sibling tools like counter_reset or counter_get.
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 for when to use this tool versus alternatives such as counter_reset or counter_parse_and_apply. The description implies permanent removal but does not explicitly mention exclusions or when users should choose this over a less destructive sibling.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get the current value and metadata for a specific counter.
| Name | Required | Description | Default |
|---|---|---|---|
| counter_id | Yes | Unique identifier for the counter |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It conveys a read-only operation via the verb 'Get' but does not disclose potential behavior like handling of nonexistent counters, authorization requirements, or side effects. The description is not misleading but omits edge-case 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?
The description is a single, front-loaded sentence with no filler. Every word contributes to understanding the tool's purpose and output.
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 is simple with one param and no output schema. The description adequately states what is returned (value and metadata), fulfilling the need for return-value context. It falls short of full completeness by not covering error cases, but for a basic get operation this is a minor gap.
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%, as the only parameter (counter_id) has a clear description in the schema. The tool description adds no additional parameter meaning, 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.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (Get), the resource (a specific counter), and the result (current value and metadata). It distinguishes itself from siblings like counter_list (all counters) and counter_history (historical values) by specifying 'a specific counter' and 'current value'.
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 usage context is implied by the name and description but not explicitly stated. There is no mention of when to use this tool versus counter_list or counter_history, nor any exclusions or alternatives. The description is sufficient for a trivial get operation but lacks explicit guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get the operation history for a specific counter, showing all increments, decrements, and resets.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum number of history entries to return (most recent). Omit to return all history. | |
| counter_id | Yes | Unique identifier for the counter |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It uses 'Get' to imply a read-only operation and specifies the content of the history, but does not disclose safety guarantees, ordering, or any side effects. The description adds some context but not comprehensive 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 a single, concise sentence that front-loads the primary action ('Get') and efficiently conveys the scope. No unnecessary words or repetition.
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 is simple with complete input schema, and the description covers purpose and content. However, without an output schema, it does not describe the exact shape or ordering of returned history entries, leaving a minor gap in how an agent interprets the 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?
The input schema already fully describes both parameters (counter_id and limit), so the description adds no additional parameter-level meaning. With 100% schema coverage, 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.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's function with a specific verb ('Get') and resource ('operation history for a specific counter'), and lists the operations covered (increments, decrements, resets). This distinguishes it from sibling tools like counter_get (current state) and counter_reset (mutation).
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 when to use the tool (when operation history is needed) but does not explicitly compare it to alternatives or state when not to use it. It lacks direct guidance such as 'use counter_get for current value'.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Increment a counter by a specified amount (default: 1). Creates the counter if it doesn't exist. Use this to track iterations, processed items, or any counting task.
| Name | Required | Description | Default |
|---|---|---|---|
| amount | No | Amount to increment by (default: 1). Can be negative to decrement. | |
| counter_id | Yes | Unique identifier for the counter (e.g., 'files_processed', 'iterations', 'step1') |
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 discloses a key side effect: 'Creates the counter if it doesn't exist.' This is essential behavior beyond the basic increment. It also mentions decrement capability via schema description, but the main description focuses on increment and auto-creation, which is appropriate.
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 two sentences, front-loaded with the primary action, and includes a purpose statement. No redundant wording or unnecessary details. Every sentence contributes value.
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?
This is a simple tool with no output schema. The description covers what it does, auto-creation behavior, and typical use cases. It does not describe the return value (e.g., new counter value), but that is not critical for invoking the tool correctly. Sibling tools are distinct and self-explanatory.
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%: both counter_id and amount are described in the input schema. The description adds context about auto-creation for counter_id, but does not add new syntax or format details beyond the schema. Thus, 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 ('Increment a counter'), the resource (counter), and the configurable amount ('by a specified amount, default: 1'). It distinguishes from siblings like counter_get, counter_reset, and counter_delete by specifying the increment 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?
The description gives explicit usage context: 'Use this to track iterations, processed items, or any counting task.' However, it does not explicitly mention alternatives or when not to use this tool, though the sibling names (counter_get, counter_reset, etc.) make the distinction obvious.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List all active counters with their current values and metadata.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It discloses that the tool lists active counters with current values and metadata, indicating a read operation. However, it does not explain what 'active' means, whether results are sorted or paginated, or if there are any side effects (unlikely but unstated). This is acceptable 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 sentence that efficiently communicates the purpose and output. Every word earns its place; there is no redundancy or 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?
Given the tool's simplicity (no parameters, no output schema), the description adequately conveys what the tool returns: active counters with values and metadata. It could be more explicit about output structure or default ordering, but for a list operation it is sufficiently complete.
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, so there is no parameter information to add. The schema is empty with 100% coverage by default. The description correctly makes no parameter claims, and the baseline for zero-parameter tools 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?
The description uses a specific verb ('List') and specifies the resource ('all active counters'), including current values and metadata. This clearly distinguishes it from sibling tools like counter_get (single counter) and counter_reset (mutation).
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 the tool is for retrieving all active counters, which provides clear context for when to use it. However, it does not explicitly mention when not to use it or reference alternatives, though the sibling names and the phrase 'all active' differentiate it from the singular get tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Parse counter tags from text and apply all operations in order. Supports multiple tag formats: Full syntax: [-counter:ID:+N-] or [-c:ID:+N-] for increment/decrement, [-counter:ID:reset-], [-counter:ID:delete-], [-counter:ID:set:N-]. Shorthand syntax (explicit numbers required): [+N:ID] for increment, [-N:ID] for decrement, [reset:ID], [delete:ID], [set:N:ID]. Examples: [+5:files], [-3:errors], [reset:temp], [set:100:progress]. Processes all tags sequentially and returns final counter states.
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | Text containing counter tags to parse and execute. Tags will be extracted and executed in order. | |
| debug | No | Enable debug mode to see detailed results for each processed tag. Default: false (streamlined mode showing only final counter states). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It discloses sequential processing, final state returns, and debug mode behavior, which is helpful. However, it does not mention error handling, what happens with invalid tags, or the mutating side effects on counters beyond 'apply operations'.
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 longer but every section earns its place: purpose, syntax forms, examples, and behavior. It is front-loaded with the primary purpose and well-structured. Slight redundancy in tag format enumeration but overall 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 complexity (multiple syntaxes) and no output schema, the description is quite complete: it covers supported formats, processing direction, debug mode, and return value. Missing error-handling details, but the core functionality is well-specified.
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 both parameters, but the description adds substantial meaning by detailing the tag syntax for the text parameter and clarifying debug output behavior beyond the schema's simple description. This elevates it above the baseline 3.
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 'Parse counter tags from text and apply all operations in order' with a specific verb and resource. It distinguishes itself from sibling tools (e.g., counter_increment, counter_reset) by targeting batch processing from text with multiple supported tag formats.
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?
Usage context is implied through the detailed tag format syntax and examples, but the description never explicitly states when to use this tool versus the individual counter operations. No exclusions or alternative recommendations are provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Reset a counter back to 0. The counter continues to exist and its history is preserved.
| Name | Required | Description | Default |
|---|---|---|---|
| counter_id | Yes | Unique identifier for the counter |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description provides key behavioral details: the counter is set to 0, it continues to exist, and history is preserved. This informs the agent about the operation's non-destructive nature.
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, no redundant information, front-loaded with the action.
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 covers the essential behavior, though it doesn't mention error handling or return values, which are likely straightforward.
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 counter_id is fully documented in the schema (100% coverage), so the description adds no additional parameter details, which is acceptable per 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?
The description uses a specific verb 'Reset' and resource 'counter', clearly defining the action and scope (back to 0). It distinguishes from siblings like counter_increment, counter_delete, and counter_get by specifying the unique behavior.
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 usage for resetting a counter while preserving its existence and history, which contrasts with counter_delete. However, it doesn't explicitly state when to use it over alternatives or when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v1.0.0counter_deletecounter_getcounter_historycounter_incrementcounter_listcounter_parse_and_applycounter_resetTools are mostly distinct: increment, reset, delete, get, list, and history each target a unique operation. However, counter_parse_and_apply can also perform increment, reset, delete, and set actions, creating some overlap with the direct tools, though it is clearly scoped as a text-parsing batch operation.
All tools follow a consistent counter_<verb> pattern, using snake_case for multi-word verbs like parse_and_apply. The naming is uniform and predictable, making it easy to infer the tool's function from its name.
With 7 tools, the server is well-scoped for a counter management domain. Each tool serves a distinct operational need without excessive overlap or redundancy, striking a balance between completeness and simplicity.
The core counter lifecycle is well covered: create (via increment), read (get/list), update (increment/reset), and delete. However, direct decrement and set-to-arbitrary-value operations are missing, requiring agents to use counter_parse_and_apply with text, which is an awkward workaround for simple cases.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
See, price, and control every tool call your AI agents make: policy checks, cost, and audit tools.
SEO & marketing toolkit for AI agents: GA4, Search Console, AdSense, GTM, PageSpeed, Trends.
OAuth 2.1 short-link tools for AI agents with scoped tokens, approvals, audit logs, and revocation.
Persistent memory and knowledge management for AI agents with semantic search and 50+ tools.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Discordit142/mcp-counter-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
