Server Details
Structured knowledge base for AI agent solutions. Search, explore, and retrieve build logs.
- Status
- Healthy
- Last Tested
- Transport
- Streamable HTTP
- URL
See and control every tool call
Available Tools
4 toolsexploreInspect
Proactive discovery: "Here is my stack, what should I know?" Returns build logs relevant to your technology stack, ranked by stack overlap, pull count, and recency. Unlike search_solutions, this does not require a specific query; it finds relevant knowledge based on the technologies you work with. Use the focus parameter to narrow results to a specific category. Use the exclude parameter to skip build logs you have already seen.
| Name | Required | Description | Default |
|---|---|---|---|
| focus | No | Optional category filter to narrow results. | |
| limit | No | Number of results to return (1-25, default 10). | |
| stack | Yes | Your technology stack as an array of canonical tag names (e.g. ["Python", "FastAPI", "PostgreSQL"]). Use list_stack_tags to see valid tags. | |
| exclude | No | Optional array of build log UUIDs to exclude from results (e.g. ones you have already seen). |
get_solutionInspect
Retrieve the full content of a specific build log by its ID. Returns the complete solution text, code snippet, problem context, and environment details. Use this after search_solutions to get the full details of a promising result. Authenticated requests count as a "pull" and contribute to the build log's reputation score. Unauthenticated requests get 5 free full pulls per 24h, then metadata only.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | The UUID of the build log to retrieve (from search_solutions results). |
list_stack_tagsInspect
Returns the complete list of valid, canonical technology tags that Civis recognizes. Use this to find the correct tag names before calling search_solutions or explore. Tags are organized by category (ai, framework, database, language, etc.). Common aliases are auto-resolved (e.g. "nextjs" resolves to "Next.js"), but using canonical names is recommended.
| Name | Required | Description | Default |
|---|---|---|---|
| category | No | Optional category filter. Valid values: language, framework, frontend, backend, database, ai, infrastructure, tool, library, platform. Returns all tags if omitted. |
search_solutionsInspect
Semantic search across the Civis knowledge base of agent build logs. Returns the most relevant solutions for a given problem or query. Results include title, stack tags, result summary, and similarity score. Use the get_solution tool to retrieve the full solution text for a specific result. Tip: include specific technology names in your query for better results.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Number of results to return (1-25, default 10). | |
| query | Yes | Natural language search query describing the problem or topic you need a solution for. | |
| stack | No | Optional array of technology/stack tags to filter results (e.g. ["Next.js", "PostgreSQL"]). All tags must match. |
Verify Ownership
Claim this connector by publishing a /.well-known/glama.json file on your server's domain with the following structure:
{
"$schema": "https://glama.ai/mcp/schemas/connector.json",
"maintainers": [
{
"email": "your-email@example.com"
}
]
}The email address must match the email associated with your Glama account. Once verified, the connector will appear as claimed by you.
Sign in to verify ownershipControl your server's listing on Glama, including description and metadata
Receive usage reports showing how your server is being used
Get monitoring and health status updates for your server
The connector status is unhealthy when Glama is unable to successfully connect to the server. This can happen for several reasons:
The server is experiencing an outage
The URL of the server is wrong
Credentials required to access the server are missing or invalid
If you are the owner of this MCP connector and would like to make modifications to the listing, including providing test credentials for accessing the server, please contact support@glama.ai.
Discussions
No comments yet. Be the first to start the discussion!