Agentcast MCP
Structured-output enforcer: extract and validate JSON from messy LLM text.
github.com/MukundaKatta · 20 listed services · provider site
Structured-output enforcer: extract and validate JSON from messy LLM text.
Token-aware message truncation: fit a chat history into your model's context budget.
Network-egress firewall for agent tools: check URLs against a declarative policy.
Snapshot tests for AI tool-call traces: diff, validate, and catch silent regressions.
Validate tool-call args before execution. Returns LLM-friendly retry hints.
Inject, parse, and strip [N] citation markers in RAG outputs.
Reliable CSV parsing + generation. Handles quotes, embedded commas, BOMs, CRLF.
Character-precise unified diff + patch application + patch parsing.
Convert HTML to Markdown or strip to plain text. For web-scraping agents.
Run JMESPath queries against JSON. Pure JS, no native binary needed.
Parse JSON5 (comments, trailing commas, unquoted keys) and emit strict JSON.
Token-budget-aware text handling: count, truncate, and chunk for LLM prompts.
Diagnose RAG drift: interpret scores, recommend thresholds, explain dimensions.
RAG retrieval IR metrics: recall@k, hit@k, MRR, NDCG@k, evaluate_batch.
Trustworthy JS regex testing. Real offsets, named groups, safe against zero-width loops.
Safe shell argument escaping for bash, cmd.exe, and PowerShell.
Deterministic SQL formatting across 19 dialects (postgres, mysql, snowflake, bigquery, etc.).
Parse partial / truncated / messy JSON for LLM tool calls and structured outputs.
IANA timezone conversions with real DST rules.
Parse, format, and convert configs across TOML, YAML, and JSON.
Provider identity is derived from the domain or repository in the source record. If two vendors share a host, they appear together here — that is a limitation of the data, not a statement about ownership.