Primitiv vs Diffgate — MCP Server Comparison | AllMCPs
Side-by-Side Model Context Protocol Comparison
Primitiv vs Diffgate
In-depth architectural comparison of the Primitiv and Diffgate MCP servers. Compare execution transports, security boundaries, tool capabilities, quality scores, and ready-to-paste client installation snippets for Claude, Cursor, Windsurf, and VS Code.
At a Glance & Executive Verdict
Primitiv
Finance & Fintech · Local stdio
Quality: 65/100 (Great) | Auth: No auth required
Diffgate
Finance & Fintech · Local stdio
Quality: 63/100 (Good) | Auth: No auth required
Verdict Summary: Choose Primitiv if you need specialized Finance & Fintech tools running via a local process. Choose Diffgate if your workspace requires Finance & Fintech integration with local subprocess execution. Both servers can be configured concurrently in your client's mcpServers manifest.
Which MCP Server Should You Choose?
Choose Primitiv when:
You need dedicated capabilities in the Finance & Fintech domain.
You prefer local stdio subprocess transport architecture.
Your security boundary fits: No auth required (Free / Open Source).
Design contract layer for your codebase. Scans Figma, code, Storybook, and token files, reconciles conflicts, and serves a single machine-readable source of truth over MCP so every agent gets the same authoritative design rules before it builds. Local-first — your code never leaves your machine.
Deterministic guardrail for AI-written diffs, runnable from inside the coding agent's own loop over MCP. Zero-LLM-token, AST-precise rules (SQLi, SSRF, XXE, permissive CORS, prototype pollution, hardcoded secrets) across 8 languages, plus structural checks for reinvented helpers and over-abstraction — findings scoped to only the changed lines, same input always gives the same output, no false-block guarantee. npm i -g diffgate-review (registers as the diffgate command; diffgate mcp starts the server)
Tools & Capabilities Breakdown
Primitiv Tools (6)
get_design_context
Get tokens, components, conflicts, inferred rules, and violation count. Default (no category) returns a summary with counts. Pass `category: "all" \
get_token
Look up a specific token by name. Pass `category` to narrow search (e.g. `"colors"`, `"spacing"`, `"borderRadius"`); aliases like `"radius"` / `"z-index"` are normalized.
get_component
Look up a specific component by name. Returns props, variants, source provenance, and `kind` — `component`, `screen`, `provider`, `icon`, or `other`, so agents reuse real UI and skip screens/providers/icons.
get_conflicts
Get conflicts between sources. Pass `type: "all" \
get_inferred_rules
Get the design rules Primitiv has extracted from your codebase patterns. Pass `category` to filter.
Ready-to-Paste Client Configurations
Paste either (or both) of these JSON server blocks into your client config file (e.g. claude_desktop_config.json or ~/.cursor/mcp.json).
Primitiv is categorized under Finance & Fintech and uses a local stdio subprocess. In contrast, Diffgate belongs to Finance & Fintech using local stdio subprocess. Select Primitiv when you need capabilities focused on finance & fintech and Diffgate when you require tools for finance & fintech.
List token-misuse violations — hardcoded literals in source that bypass the contract, with a suggested token when one fits. Pass `category: "all" \
Diffgate Tools (7)
diffgate_analyze
Analyze a file for code review findings. Only flags risk on lines changed vs the git baseline (diff-aware). Pass `content` to analyze unsaved or generated code before it is written to disk. When a code graph is available, public-surface findings carry an `impact` field (caller count, suggested reviewers, test gaps) and may be tier-adjusted — fix high-blast-radius findings before surfacing the code.
diffgate_check_staged
Check all staged (or working-tree) changes in a git repo for DiffGate findings. Returns overall tier, counts, and per-file findings across the whole diff, plus a `verdict` block (the agent autonomy ladder: pass/review/blocked overall, with a rung — block/escalate/autofix/advisory — per finding) so you can decide whether to surface the diff without reimplementing the rules.
diffgate_deep_review
Run an agentic deep review on a single high-impact (orange) finding. The model uses real repo tools (grep, read_file, find_references, git_blame) to investigate blast radius before rendering a verdict.
diffgate_explain
Get a concise AI explanation for a DiffGate finding. Faster than diffgate_deep_review — a single LLM call with no tool loops.
diffgate_capabilities
Report which DiffGate layers are active (core / code graph / LLM), which tools you can call right now without an error, and the agent autonomy budget (fix limit, escalation, trust source). Call this once up front so you know what's available instead of discovering it via thrown errors.
diffgate_guidelines
Review the diff against the repo's own coding guideline files (AGENTS.md, CLAUDE.md, .cursorrules, etc.), scoped per directory (nearest file wins). IMPORTANT: if the result has mode='host', NO external model was used — this is a SELF-REVIEW, not an independent gate: YOU (the calling agent) evaluate each group's `hunks` against its `guidelines` text using your own model. Treat host-mode results as ADVISORY only — never block the change on them. If mode='model', findings were produced by the configured provider and are returned directly.
diffgate_feedback
Record a reviewer's verdict on a finding so DiffGate learns. verdict 'dismiss' suppresses that same flagged code (ruleId + code) in future reviews (noise reduction); 'confirm' marks it as a real, valued catch. Stored in .diffgate/learnings.json at the repo root.