/glama/servers/score

POST /api/glama/servers/score

Price: 1 credit

Get Glama's full scoring breakdown for one MCP server. Returns the maintenance grade with the commit, issue-response, release and security-alert evidence behind it, the packaging checks Glama runs (readme, glama.json, inspectability, recent usage), the server-level quality score with its written justifications, and a per-tool documentation score with the specific weaknesses Glama flagged.

How to use it

Reach for this when you have to justify a ranking rather than produce one: `maintenance_details` and `tool_scores[].score.smells` carry the evidence and the named weaknesses, which /glama/servers gives only as letter grades. `tool_scores[].score.summary` is written prose about a single tool's documentation quality, not about whether the tool works. Everything here is Glama's own assessment of the repository, so an ungraded server returns the record with the score fields null rather than a 412.

Parameters

• access-token string required

Request body

• timeout integer — Max scrapping execution timeout (in seconds) (default: 300; min: 20; max: 1500)
• server string required — Glama server id in namespace/slug form, or the address of its Glama page (examples: "korotovsky/slack-mcp-server", "@korotovsky/slack-mcp-server", "https://glama.ai/mcp/servers/korotovsky/slack-mcp-server"; minLength: 1)

Response

• @type string (default: "GlamaServerScore")
• id string required
• url string required
• maintenance_tier string nullable
• latest_release_version string nullable
• tool_count integer nullable
• recent_usage integer nullable
• has_readme boolean nullable
• has_glama_json boolean nullable
• has_recent_usage boolean nullable
• has_user_submitted_related_servers boolean nullable
• is_inspectable boolean nullable
• quality_score object nullable
  • @type string (default: "GlamaServerQualityScore")
  • overall_score number nullable
  • overall_tier string nullable
  • coherence_score number nullable
  • coherence_tier string nullable
  • coherence_summary string nullable
  • coherence_justifications object nullable
  • description_quality_score number nullable
  • description_quality_tier string nullable
  • completeness number nullable
  • disambiguation number nullable
  • naming_consistency number nullable
  • tool_count_appropriateness number nullable
  • mean_tdqs number nullable
  • min_tdqs number nullable
  • tool_count integer nullable
  • scored_tool_count integer nullable
  • scored_at string nullable
• maintenance_details object nullable
  • @type string (default: "GlamaMaintenanceScoreDetails")
  • archived boolean nullable
  • total_commits integer nullable
  • issues_handled_count integer nullable
  • issues_total_count integer nullable
  • latest_release_published_at string nullable
  • ci_passing boolean nullable
  • code_scanning_error_count integer nullable
  • critical_alert_count integer nullable
  • high_alert_count integer nullable
• tool_scores array (default: [])
  • @type string (default: "GlamaToolScore")
  • name string required
  • score object nullable
    • @type string (default: "GlamaToolQualityScore")
    • tdqs number nullable
    • tier string nullable
    • summary string nullable
    • smells array (default: [])
    • purpose_clarity number nullable
    • parameter_semantics number nullable
    • usage_guidelines number nullable
    • behavioral_transparency number nullable
    • contextual_completeness number nullable
    • conciseness_structure number nullable
    • justifications object nullable

Errors

• 422 — The request body did not validate Check the fields against this schema. A URN with the wrong prefix is the most common cause.
• 408 — The request ran past its time limit Raise `timeout` in the request body, up to the maximum this endpoint documents. Lowering `count` or turning off the `with_*` flags also helps, because less work finishes sooner.
• 412 — No Glama server carries this namespace/slug id Retrying will not help: either the entity does not exist, or the input points at a different one.
• 429 — Too many requests: a rate limit or a usage window is exhausted When the response carries an X-Retry-After header, wait that many seconds and retry: the same number is in the body as `detail.retry_after`, and the limit clears once that window passes. The message in the body names the limit that was hit.
• 500 — Something broke on our side Retrying will not help. If it keeps happening, send us the X-Request-ID from the response headers.
• 529 — Rate limit reached, or the endpoint is overloaded Wait at least 30 seconds, then retry.

Response headers

• X-Error — Error message text (present only on error)
• X-Request-ID — Unique request identifier
• X-Execution-Time — Execution time in seconds
• X-Result-Count — How many records the body carries. 0 means an empty result, which is a normal answer and not by itself an error. A non-zero count can come back together with X-Error when the failure happened partway through — read this header and X-Error independently.
• X-Total-Available-Results — How many records exist for this query, when the endpoint can say. On a `dry_run` request this is the answer and the body is empty. It saturates: the endpoint's documented maximum means 'at least that many', any smaller number is exact.
• X-Warning — Present when the request body carried keys this endpoint does not document. They were ignored, so any filter you meant to apply through them did not apply. Check the spelling against this schema and retry.
• X-Retry-After — Seconds to wait before retrying. Present only on 429.