[mcp-analysis] MCP Structural Analysis - 2026-05-15 #32358
Replies: 1 comment
-
|
💥 KA-POW! 🦸♀️ The Smoke Test Squad just WHOOSHED through this discussion! 🌪️ ⚡ ZAP! All systems nominal! 💪 ...and that's another one for the smoke-test scrapbook! 📚✨ Warning Firewall blocked 6 domainsThe following domains were blocked by the firewall during workflow execution:
network:
allowed:
- defaults
- "accounts.google.com"
- "android.clients.google.com"
- "clients2.google.com"
- "contentautofill.googleapis.com"
- "safebrowsingohttpgateway.googleapis.com"
- "www.google.com"See Network Configuration for more information.
|
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
Overview
Analyzed 12 GitHub MCP tools across 10 toolsets for response size, schema structure, and usefulness in agentic workflows.
Headline Findings
get_file_contents,list_pull_requests,search_repositories(⭐⭐⭐⭐⭐)get_me(⭐ — 403 in this environment)list_workflows(~2,200 tok),list_label(~2,125 tok)Key insight: Pagination is inconsistent.
list_workflowsandlist_labelignoredperPage=1/ had no perPage support and returned the entire collection (296 workflows, 534 labels) — a large hidden context cost that agents should anticipate.Critical Issues
get_mereturns 403 Resource not accessible by integration under the workflow's installation token — agents that depend on identity discovery will fail silently.list_labelhas noperPageparameter and dumps all repository labels regardless of need. Useget_labelwhen only one is needed.list_workflowsreturns the entire workflow set even whenper_page=1is supplied.Full Structural Analysis Report
Usefulness Ratings for Agentic Work
get_file_contentslist_pull_requestssearch_repositorieslist_code_scanning_alertslist_discussionslist_brancheslist_commitsauthorandcommit.author.list_issueslist_tagsget_tagfor date/message.list_workflowslist_labelget_meSchema Analysis
get_file_contentslist_pull_requestssearch_repositorieslist_code_scanning_alertslist_discussionslist_brancheslist_commitslist_issueslist_tagslist_workflowslist_labelget_meResponse Size by Toolset (today)
30-Day Trend
Recommendations
get_file_contents,list_pull_requests,search_repositories,list_code_scanning_alerts,list_discussions,list_branches,list_commits. Use these as the default for agentic GitHub workflows.list_workflows— honorper_page; trimnode_id/badge_urlfrom default response.list_label— addperPagesupport; default to small page sizes.get_me— surface installation-token limitations earlier with a clearer error.list_code_scanning_alerts,list_branches,list_discussions,search_repositories.list_workflows,list_label.search_repositoriesminimal_output: true) — they materially reduce token cost.Visualizations
Response Size by Toolset
Usefulness Ratings
Daily Token Trend
Size vs Usefulness
References:
Note
🔒 Integrity filter blocked 1 item
The following item was blocked because it doesn't meet the GitHub integrity level.
*.lock.ymlfiles quote the top-levelon:key #32354list_issues: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".To allow these resources, lower
min-integrityin your GitHub frontmatter:Beta Was this translation helpful? Give feedback.
All reactions