topai-mcp-suite
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| agentpr_guard_auditB | Audit a git diff or Pull Request for AI-hallucinated packages, typosquatting, and architecture boundary breaches. |
| tokenprune_wasm_trimA | Prune TypeScript/JavaScript source code to reduce LLM context token usage by 50%-70% by collapsing method bodies. |
| dockerlean_wasm_auditA | Audit a Dockerfile statically for layer bloat, cache invalidation, root user, and missing multi-stage build. |
| cidr_shield_lookupA | Query an IPv4 address with 0ms latency to detect Datacenter/Cloud servers, VPNs, Tor, and bot proxies. |
| terracost_blast_evaluateA | Evaluate a Terraform JSON plan for blast radius, stateful resource destruction, and monthly FinOps cost delta. |
| pack3d_wasm_packC | 3D bin packing optimizer. Packs multiple 3D items into available cartons with 6-axis orthogonal rotation. |
| flaky_quarantine_analyzeC | Analyze test stability from multiple JUnit XML runs using Markov chain transition matrices. |
| sqltwin_stream_anonymizeB | Anonymize raw SQL dump content preserving 100% of foreign key joins and unique constraints. |
| edgarpulse_parse_filingA | Parse SEC Form 4 or 8-K XML filing to detect C-suite open market cluster purchases with quantitative conviction score. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 9 tools
Each tool targets a clearly distinct resource and action (e.g., audit PR, audit Dockerfile, lookup IP, evaluate Terraform plan, pack 3D items), so an agent can easily distinguish them. The only shared verb is 'audit' but the targets differ completely.
All nine names follow a consistent snake_case pattern of [prefix]_[modifier]_[verb], with the verb last (audit, trim, lookup, evaluate, pack, analyze, anonymize, parse). No mixed conventions or vague verbs.
9 tools is well within the 3-15 sweet spot for a utility suite; each tool has a distinct, non-redundant purpose and earns its place. No obvious bloat or thinness.
The suite spans many unrelated domains (code audit, Docker, IP intelligence, Terraform cost, 3D packing, test flakiness, SQL anonymization, SEC filings), so no single domain gets complete lifecycle/CRUD coverage. Many tools are analysis-only with no companion 'fix' or 'apply' operations, creating dead ends for follow-up actions, though each is self-contained for its stated task.