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., "@bragdoc-mcp let's capture my recent project achievement using STAR"
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.
An MCP server that helps you capture professional achievements using the STAR method. Claude interviews you — asking questions iteratively — until each achievement is captured with quantified impact and business outcomes. Once your achievements are logged you can generate period summaries and performance review self-assessments, all from Claude Desktop.
Node.js 18+
Claude Desktop (or any MCP-compatible client)
Related MCP server: interview-mcp-server
No install required. Run directly via npx:
npx -y bragdoc-mcpAdd to your Claude Desktop MCP config file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"bragdoc": {
"command": "npx",
"args": ["-y", "bragdoc-mcp"]
}
}
}Restart Claude Desktop after saving.
All data is stored locally at ~/.bragdoc/:
brag.json — your achievements
competencies.json — your role competency framework
goals.json — your OKRs for the current review cycle
Once connected, try these prompts in Claude Desktop:
Capture an achievement:
Use the "Add Achievement" prompt — Claude will interview you using the STAR method until every field is captured with quantified impact.
Weekly review:
Use the "Weekly Update" prompt — Claude checks what you accomplished and suggests new achievements to capture.
Set up context (do this once):
Use "Set Up Competencies" to enter your organisation's competency framework. Use "Set Up Goals" to enter your OKRs for the current review cycle.
Generate a summary or review:
Use "Period Summary" with a period like "Q1 2026" or "March 2026". Use "Performance Review" with your review period to generate a structured self-assessment.
Tool | Description |
| Add an achievement with STAR fields |
| List achievements with optional date/tag/keyword filters |
| Retrieve a single achievement by ID |
| Update any field of an existing achievement |
| Delete an achievement |
| Retrieve your competency list |
| Save your competency list |
| Retrieve your goals list |
| Save your goals list |
Three MCP resources are exposed for direct data access:
bragdoc://achievements
bragdoc://competencies
bragdoc://goals
git clone https://github.com/YOUR_USERNAME/bragdoc-mcp
cd bragdoc-mcp
npm install
npm run build
npm testFor local Claude Desktop development, use an absolute path in the config:
{
"mcpServers": {
"bragdoc": {
"command": "node",
"args": ["/absolute/path/to/bragdoc-mcp/dist/index.js"]
}
}
}Create a new achievement using the STAR method. Returns the created achievement with its generated UUID.
| Name | Required | Description | Default |
|---|---|---|---|
| date | Yes | ISO 8601 date of the achievement e.g. 2026-02-28 | |
| tags | No | Optional tags | |
| task | Yes | Your specific responsibility (T in STAR) | |
| action | Yes | What you did (A in STAR) | |
| result | Yes | Quantified business impact — numbers, %, business outcomes (R in STAR) | |
| headline | Yes | One-line summary of the achievement | |
| situation | Yes | Context and background (S in STAR) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden. It discloses the return value (created achievement with UUID) but does not mention side effects, idempotency, or required permissions. Adequate but could be richer.
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 concise sentences with no wasted words. It front-loads the core purpose and includes a clear statement of return 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?
Despite no output schema and no annotations, the description is minimal. It explains purpose and return, but lacks usage context, behavioral notes, or parameter details beyond schema. Adequate for a simple create tool but could be more helpful.
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% – all parameters have descriptive schema descriptions. The tool description reinforces the STAR method but does not add additional meaning beyond the schema. 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 verb 'Create', the resource 'achievement', the method 'STAR method', and what is returned ('created achievement with its generated UUID'). It distinguishes from siblings like 'update_achievement' and 'delete_achievement'.
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 creating a new achievement but does not explicitly contrast with alternatives (e.g., 'update_achievement' for existing ones). No exclusions or when-not-to-use guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Delete an achievement by its UUID id.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | UUID of the achievement to delete |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden but only says 'Delete an achievement'. It does not disclose consequences, permissions required, or any side effects beyond the basic 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?
The description is a single clear sentence with no wasted words. However, it is extremely brief and could include more context without losing conciseness.
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 simplicity (one parameter, no output schema), the description is minimally complete. It lacks information on success/failure responses or deletion confirmation, but covers the core action.
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 description mirrors the schema description. The description adds no additional meaning beyond what the schema already provides, 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 explicitly states the verb 'Delete', the resource 'achievement', and the identifier 'UUID id'. It clearly distinguishes from sibling tools like update_achievement and list_achievements.
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 no guidance on when to use this tool vs alternatives, no prerequisites, no warnings about irreversible actions, and no context about 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.
Retrieve a single achievement by its UUID id.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | UUID of the achievement |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It correctly identifies a read operation but does not disclose behavior for invalid IDs or non-existent achievements. However, for a simple retrieval, the basic behavior is clear.
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, efficient sentence with no extraneous words. It immediately conveys the tool's purpose.
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 retrieval tool with one parameter and no output schema, the description is mostly complete. It could mention the return format or error handling, but the core functionality is clear.
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 the single parameter 'id' with description 'UUID of the achievement'. The tool description adds no additional meaning beyond what is in the schema, so baseline score 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 'Retrieve', the resource 'a single achievement', and the identifier 'by its UUID id'. It is specific and distinguishes itself from sibling tools like 'list_achievements' which retrieves multiple.
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 no guidance on when to use this tool versus alternatives such as 'list_achievements' for multiple achievements or 'get_goals' for other resources. It does not mention exclusions or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Retrieve the user's stored competency framework. Returns an array of competencies (name, description, optional level).
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It only discloses the return format but omits behavioral traits like read-only nature, authentication, or error handling.
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 that is efficiently front-loaded with purpose and content description, 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?
For a simple parameterless tool, it describes the return format clearly. Minor gaps like error states or empty results are not addressed, but acceptable given 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?
No parameters exist, so baseline 4 applies. Description adds no param info because none are needed.
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?
Description clearly states 'Retrieve the user's stored competency framework' with a specific verb and resource. It distinguishes from sibling 'set_competencies' as a write alternative.
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?
Implies usage for reading competencies, with a sibling 'set_competencies' for writing, but no explicit when-not-to-use or prerequisites are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Retrieve the user's stored OKR goals. Returns an array of goals (title, description, targetDate).
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description carries full burden. It discloses the return structure (array of goals with specific fields) but does not state behavioral traits like authentication requirements, rate limits, or whether it returns only the current user's goals. The read-only nature is implied by the name but not explicit.
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, front-loaded with purpose and output details. Every sentence is essential and concise. 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 retrieval tool with no parameters and no output schema, the description is complete. It tells the agent what the tool does, what it returns, and is sufficient for correct invocation.
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 the baseline is 4. The description adds value by explaining what the output contains, which compensates for the lack of schema details. No parameters to document.
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 'Retrieve', the resource 'the user's stored OKR goals', and specifies the output format (array with title, description, targetDate). This distinguishes it from sibling tools like set_goals (write) and get_technologies (different resource).
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 reading OKR goals, which is clear from the context of sibling tools. However, it does not explicitly state when to use this tool versus alternatives like get_achievement, leaving some ambiguity for agents with limited context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List achievements with optional filters: date range, tags (AND match), and keyword search.
| Name | Required | Description | Default |
|---|---|---|---|
| to | No | Inclusive end date (ISO 8601) | |
| from | No | Inclusive start date (ISO 8601) | |
| tags | No | All specified tags must be present (AND) | |
| keyword | No | Case-insensitive substring match across all text fields |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description is sole source. It discloses filter behaviors (AND match for tags, case-insensitive substring for keyword). However, it omits return format, pagination, sorting, or error handling, which are important for a listing tool.
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 conveys all key information with zero waste. Front-loaded with purpose and filters.
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 4 optional parameters, no output schema, and no annotations, the description covers filter semantics but lacks details on pagination, ordering, or response structure. Adequate for simple use but not fully 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?
Schema has 100% coverage with descriptions. Description rephrases filter semantics (date range, tags AND match, keyword case-insensitive) but adds limited new meaning beyond schema. 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?
Clear verb 'list' and resource 'achievements' with specific filter types (date range, tags, keyword). Distinguishes from siblings like get_achievement (single item) and CRUD tools.
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?
Implied usage: use for filtered listing of achievements. Does not explicitly mention when to prefer siblings (e.g., get_achievement for single item), but context is clear enough.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Store the user's competency framework. Replaces any existing competencies entirely.
| Name | Required | Description | Default |
|---|---|---|---|
| competencies | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It discloses the critical destructive behavior: 'Replaces any existing competencies entirely.' This is sufficient for a simple store operation, though it omits details like output or idempotency.
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 verb-object pair, followed by the key behavioral note. 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?
Despite low complexity (one parameter), the description lacks schema guidance due to 0% coverage. It does not compensate with parameter explanations, leaving the agent without enough context to construct valid input. Sibling tools like get_competencies could help but are not referenced.
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?
Given 0% schema description coverage, the description must explain parameters but does not. It only says 'Store the user's competency framework' without describing the structure of the competencies array. The agent cannot infer required fields or format from the description alone.
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 identifies the tool's action ('Store the user's competency framework') and the specific resource. It also explicitly states that it replaces existing competencies entirely, distinguishing it from incremental update tools like update_achievement.
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 full replacement rather than incremental updates, but it does not explicitly state when to use it versus alternatives (e.g., set_goals or add_achievement). No direct comparison or contraindications are provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Store the user's OKR goals. Replaces any existing goals entirely.
| Name | Required | Description | Default |
|---|---|---|---|
| goals | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
In the absence of annotations, the description discloses the key behavioral trait: it entirely replaces existing goals. This informs the agent of the destructive nature. No further side effects are mentioned, but the core behavior is clear.
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 no unnecessary words. Every sentence adds value: first states purpose, second clarifies behavior.
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 tool with one parameter and no output schema, the description covers purpose and behavioral effect. It could mention return value or confirmation, but the essential information 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?
The input schema already provides descriptions for each property (title, targetDate, description), so the schema itself offers strong parameter semantics. The description adds little beyond naming the goals as 'OKR goals', 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 verb 'store' and the resource 'OKR goals', and distinguishes itself by mentioning it replaces existing goals entirely, setting it apart from sibling tools like add_achievement or get_goals.
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 it (to set all goals) by stating it replaces existing goals, but does not explicitly exclude use cases like partial updates. However, the contrast with sibling tools is evident.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Partially update an achievement. Only the supplied fields are changed; all others are preserved.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | UUID of the achievement to update | |
| date | No | ISO 8601 date | |
| tags | No | ||
| task | No | ||
| action | No | ||
| result | No | ||
| headline | No | ||
| situation | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description must disclose behavioral traits. It states 'partial update' but does not mention side effects, required permissions, error handling (e.g., if id not found), or whether changes are reversible. This is insufficient for a mutation tool.
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 with no wasted words. It is front-loaded with the key action and efficiently conveys the partial update behavior.
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 8 parameters, no output schema, and no annotations, the description is insufficient. It does not explain return values, error cases, or authentication needs. For a partial update tool, more context is needed for correct invocation.
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 low (25%), with only the id parameter having a description. The tool description does not add meaning to any parameters beyond the schema. It mentions that only supplied fields are changed, but does not explain what each optional field represents.
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 ('partially update') and the resource ('an achievement'), and distinguishes this tool from siblings like add_achievement and delete_achievement. It specifies that only supplied fields are changed, which is precise and unambiguous.
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 modifying specific fields of an achievement without affecting others, but lacks explicit guidance on when to use it versus alternatives (e.g., delete then add). No context about prerequisites or exclusions is provided.
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.
v1.0.1add_achievementdelete_achievementget_achievementget_competenciesget_goalslist_achievementsset_competenciesset_goalsupdate_achievementScored across 9 tools
Each tool targets a distinct operation on a specific resource: achievements have full CRUD plus list, competencies and goals have get/set. No overlap in functionality.
All tool names follow a consistent verb_noun pattern using snake_case (e.g., add_achievement, set_competencies). Predictable and clear.
9 tools cover the brag document domain well: CRUD for achievements, get/set for competencies and goals. Not too many or too few.
Achievements have full lifecycle (create, read, update, delete, list with filters). Competencies and goals have get and replace-all set, which is sufficient for typical use. No obvious gaps.
Privacy-first work tracking with summaries, reports, coaching, and AI-ready long-term memory.
Career assistant: resumes, job-match analysis, interview results and career memory.
Log, search and summarise your work history in Roleora, the career record for professionals.
Capture and organize private career evidence as career memories.
