evergreen-mcp-server

Official

by evergreen-ci

Overview Schema Related Servers Score Discussions

Python

Remote

Server Quality Checklist

Profile completionA complete profile improves this server's visibility in search results.

Latest release: v0.5.0
Disambiguation4/5
Most tools have distinct purposes, but the summary/detailed pairs (get_task_log/get_test_results) could cause initial confusion. However, descriptions clearly contrast them, reducing ambiguity.
Naming Consistency3/5
Naming patterns are inconsistent: some tools end with '_evergreen', others don't; verbs vary (download, get, list); 'detailed' and 'summary' are used as suffixes but not consistently across all tools.
Tool Count5/5
8 tools is a reasonable count for a CI/CD debugging server, covering artifact downloads, log retrieval, test results, and patch listing without being excessive.
Completeness5/5
The tool set provides comprehensive retrieval capabilities for debugging failures: from listing patches and failed jobs to detailed logs and test results. No obvious gaps for the intended use case.
Average 4.4/5 across 8 of 8 tools scored. Lowest: 3.8/5.
See the Tool Scores section below for per-tool breakdowns.
- No community issues in the last 6 months
- 10 commits in the last 12 weeks
- Last stable release on February 18, 2026
- No critical vulnerability alerts
- No high-severity vulnerability alerts
- No code scanning findings
- CI is passing
Add a LICENSE file by following GitHub's guide. Once GitHub recognizes the license, the system will automatically detect it within a few hours.
If the license does not appear after some time, you can manually trigger a new scan using the MCP server admin interface.
MCP servers without a LICENSE cannot be installed.
This repository includes a README.md file.
No tool usage detected in the last 30 days. Usage tracking helps demonstrate server value.
Tip: use the "Try in Browser" feature on the server page to seed initial usage.
Add a glama.json file to provide metadata about your server.
If you are the author, simply .
If the server belongs to an organization, first add glama.json to the root of your repository:
```
{
  "$schema": "https://glama.ai/mcp/schemas/server.json",
  "maintainers": [
    "your-github-username"
  ]
}
```
Then . Browse examples.
Add related servers to improve discoverability.

How to sync the server with GitHub?

Servers are automatically synced at least once per day, but you can also sync manually at any time to instantly update the server profile.

To manually sync the server, click the "Sync Server" button in the MCP server admin interface.

How is the quality score calculated?

The overall quality score combines two components: Tool Definition Quality (70%) and Server Coherence (30%).

Tool Definition Quality measures how well each tool describes itself to AI agents. Every tool is scored 1–5 across six dimensions: Purpose Clarity (25%), Usage Guidelines (20%), Behavioral Transparency (20%), Parameter Semantics (15%), Conciseness & Structure (10%), and Contextual Completeness (10%). The server-level definition quality score is calculated as 60% mean TDQS + 40% minimum TDQS, so a single poorly described tool pulls the score down.

Server Coherence evaluates how well the tools work together as a set, scoring four dimensions equally: Disambiguation (can agents tell tools apart?), Naming Consistency, Tool Count Appropriateness, and Completeness (are there gaps in the tool surface?).

Tiers are derived from the overall score: A (≥3.5), B (≥3.0), C (≥2.0), D (≥1.0), F (<1.0). B and above is considered passing.

Tool Scores

Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must fully disclose behavioral traits. It explains the tool scans recent patches up to max_patches and sorts by activity, but does not mention potential performance implications of scanning up to 50 patches, error cases, or authentication details beyond the optional bearer token. These gaps are acceptable for a simple read operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences: the first clearly states the primary action and output, the second adds context about sorting and usefulness. There is no redundant or extraneous information. It is appropriately sized and front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (2 optional parameters, output schema exists), the description covers the key aspects: what it does, how it works (scanning recent patches), and why it's useful. It does not detail the output format or error handling, but the output schema likely covers format. For a read-only discovery tool, it is sufficiently complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% according to context signals, with both parameters well-documented in the input schema. The description adds value by explaining the sorting logic and the inference mechanism, but does not significantly expand on the schema's existing parameter descriptions. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Get a list of unique project identifiers inferred from the user's recent patches.' It specifies the verb (get), resource (project identifiers), and method (inferred from patches). The additional context about sorting by activity and usefulness for understanding project context distinguishes it from sibling tools like list_user_recent_patches_evergreen.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description mentions the tool is 'useful for understanding project context and filtering other queries,' which implies when to use. However, it does not explicitly state when not to use or provide direct comparisons to sibling tools. The guidance is adequate but lacks explicit exclusion or alternative suggestions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It mentions 'downloaded to a local directory structure organized by version' but does not disclose potential issues like overwrite behavior, permission requirements, rate limits, or error handling for invalid task IDs.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, no unnecessary words. First sentence states the purpose, second provides additional context. Very concise and front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Although an output schema exists, the description does not mention what the tool returns (e.g., list of downloaded file paths). It only describes the local directory effect. For a download tool, return behavior is important for agents to process results.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema description coverage is 100%, with all four parameters described adequately. The description adds minimal extra meaning beyond the schema (e.g., 'organized by version'). Baseline is 3 for high coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Download artifacts from a specific Evergreen task' and lists examples like build outputs, test results, logs. It uses a specific verb and resource, and distinguishes from sibling tools that are read-only get/list operations.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description tells when to use this tool ('retrieve build outputs, test results, logs, or other files generated by a task') but does not explicitly mention when not to use or compare with sibling tools like get_task_log_* for log content.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses automatic error pattern scanning and structured summary, but with no annotations, more could be added (e.g., response size, auth requirements, destructive potential). No contradiction with annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Four sentences, front-loaded with purpose, no redundancy. Every sentence adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given output schema exists (not shown) and no annotations, description sufficiently covers return value (full logs + error summary). Slightly lacking in response size disclosure, but adequate for the tool's complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so description adds marginal value. It reinforces task_id source but does not provide new meaning beyond schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states it gets complete raw task logs via REST API, and distinguishes from the GraphQL get_task_log_summary tool by listing content it can access (timeout handler output, process dumps, stdout/stderr).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly recommends use for debugging non-test failures and references get_patch_failed_jobs as source for task_id. Does not explicitly state when not to use or provide alternatives for test failures, but the differentiation from get_task_log_summary is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses auto-detection behavior for project_id, potential return of project list, and recommends user interaction. While no annotations are present, the description covers key behavioral aspects; however, it could note that the tool is read-only.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Description is concise (4-5 sentences) and front-loaded with purpose. Each sentence adds value, but it could be slightly tighter. Overall well-structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the existence of an output schema, the description effectively covers what the tool does, the parameters, and edge cases (missing project_id). It is complete for an analysis tool with moderate complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Adds meaning beyond the 100% schema coverage by explaining the purpose of patch_id and project_id, and providing usage guidance for max_results ('10-20 for focused analysis, 50+ for comprehensive review'). This adds value for the agent.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Analyze failed CI/CD jobs for a specific patch to understand why builds are failing.' It specifies the verb (analyze) and resource (failed CI/CD jobs) and is distinct from sibling tools that focus on individual tasks or test results.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides explicit guidance on when to use ('Essential for debugging patch failures') and how to handle missing project_id (ask user to specify). It does not explicitly exclude scenarios but gives sufficient context for appropriate use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, description fully carries behavioral disclosure. It reveals the tool fetches from S3, not GraphQL, automatically scans for error patterns, and returns a structured summary with top error terms and example lines. This goes beyond a simple 'get content' description, though it doesn't detail auth mechanics or rate limits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Description is extremely concise: two sentences covering core functionality, plus a short usage guideline. Every sentence adds value, no redundancy. Front-loaded with primary purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's moderate complexity (5 parameters, output schema exists), the description covers core functionality, usage context, output characteristics (error scan), and prerequisites. It is self-contained and complete for an agent to understand invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, but description adds valuable context beyond schema. For test_name, it explains typical values for resmoke tests; for tail_limit, it clarifies default purpose; for task_id, it specifies source. This enriches parameter understanding.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the tool fetches raw test log content from S3, explicitly distinguishing it from GraphQL-based tools. It provides specific verb+resource (Get raw test log content) and hints at its unique value (scanning for error patterns). The purpose is clear and differentiates from sibling tools like get_test_results_summary and get_task_log_summary.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly states when to use: to understand WHY a test failed. Provides prerequisite: requires task_id and test_name from get_patch_failed_jobs. However, does not explicitly mention when not to use or list alternative tools, though context implies summary tools are for lighter needs.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description fully discloses that the tool returns only a limited portion of the full log (mostly test log ingestion messages) and directs users to the detailed version for complete logs. No contradictions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise (3 sentences) and front-loaded with the core purpose. Every sentence adds value: purpose, limitation, alternative, and data source. No redundant words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the presence of an output schema (not shown) and comprehensive parameter schema, the description covers all necessary context: what it does, its limitations, when to use the sibling, and where to get the input. It is complete for an agent to decide and invoke correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with detailed descriptions for each parameter. The tool description adds minimal parameter-specific value beyond the schema, though it reiterates the source of task_id. Baseline of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool gets a truncated view of task logs via GraphQL, specifies it returns log metadata and filtered error/failure messages, and explicitly distinguishes it from the sibling tool get_task_log_detailed for complete logs. The verb 'get' and resource 'task_log_summary' are specific.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit when-to-use guidance (truncated view, error analysis) and when-not-to-use (for complete logs, use get_task_log_detailed). It also gives a concrete tip: 'Use task_id from get_patch_failed_jobs results.'
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. Discloses auto-detection of project_id, returned list of available IDs if undetermined, and that it returns patch IDs. Lacks mention of rate limits or authentication details beyond bearer token.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Four sentences, front-loaded with core purpose. No wasted words; structure logically flows from purpose to usage to parameter details.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Output schema exists, so return values not needed. Covers auto-detection behavior and project_id handling, but omits pagination or historical depth. Generally sufficient for a list tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters5/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% (baseline 3), but description adds valuable context: usage tips for limit, auto-detection behavior for project_id, and bearer token override. Enhances parameter understanding beyond schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states 'Retrieve the authenticated user's recent Evergreen patches/commits with their CI/CD status', specifying verb, resource, and scope. Distinguishes from siblings by focusing on user's recent patches.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly says 'Use this to see your recent code changes, check patch status...' and provides guidance on handling missing project_id (ask user). Differentiates from sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It discloses that the tool uses GraphQL and does not return error messages. While it covers the main behavioral trait (what is omitted), it could be slightly more detailed about the scope or performance implications, but overall it is transparent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Three sentences that are dense with information. No wasted words. Purpose is front-loaded, then differentiation, then usage pointer.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (5 params, 1 required, output schema exists), the description fully explains what the tool returns and what it doesn't. It provides sufficient context for an AI agent to know when to call this tool and what to expect.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters5/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with all 5 parameters described. The description adds substantial context beyond the schema: recommended ranges for limit, source of task_id, meaning of execution, recommendation for failed_only, and explanation of bearer_token override.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool gets test result metadata (test names, pass/fail, durations, Parsley URLs) and explicitly says what it does NOT return (actual error messages). It distinguishes itself from the sibling tool get_test_results_detailed.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides explicit guidance: 'For the raw test log content with error pattern analysis, use get_test_results_detailed instead.' Also instructs to 'Use task_id from get_patch_failed_jobs results', which clarifies the prerequisite and context of use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

GitHub Badge

Glama performs regular codebase and documentation scans to:

Confirm that the MCP server is working as expected.
Confirm that there are no obvious security issues.
Evaluate tool definition quality.

Our badge communicates server capabilities, safety, and installation instructions.

Card Badge

Copy to your README.md:

[![evergreen-mcp-server MCP server](https://glama.ai/mcp/servers/evergreen-ci/evergreen-mcp-server/badges/card.svg)](https://glama.ai/mcp/servers/evergreen-ci/evergreen-mcp-server)

Score Badge

Copy to your README.md:

[![evergreen-mcp-server MCP server](https://glama.ai/mcp/servers/evergreen-ci/evergreen-mcp-server/badges/score.svg)](https://glama.ai/mcp/servers/evergreen-ci/evergreen-mcp-server)

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

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/evergreen-ci/evergreen-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server