6.6mediumCONDITIONAL GO

MCP Permission Manager

Granular permission control layer for AI agent tool access across CLIs and APIs

DevToolsEngineering teams and enterprises using AI coding agents (Claude Code, Copilo...
The Gap

Current AI agent frontends like Claude Code only support one level of CLI permission authorization, making it absurd to grant broad access like 'az vm:*' when you only need specific subcommands

Solution

A permission middleware that sits between AI agents and tools/CLIs/APIs, offering fine-grained, policy-based access control with audit logging and approval workflows

Revenue Model

subscription - free tier for individual devs, paid tiers for teams with audit logs, SSO, and policy templates

Feasibility Scores
Pain Intensity7/10

The pain is real but currently felt by a narrow audience — power users running AI agents with cloud CLI access. Most devs haven't hit this wall yet because they're not giving agents broad tool access. Pain will intensify dramatically as agent autonomy increases over the next 6-12 months. The 'az vm:*' example resonates strongly with anyone who's tried it.

Market Size6/10

TAM is currently small but growing fast. ~500K developers actively using AI coding agents with tool access today, maybe 10% hitting permission pain points. At $20/seat/mo for teams, near-term SAM is ~$12M/year. But this could 10x in 18 months as agentic AI goes mainstream in enterprise. The ceiling is high, the floor right now is low.

Willingness to Pay5/10

Individual devs will not pay — they'll use workarounds or accept coarse permissions. Enterprise security/compliance teams WILL pay, but the sales cycle is long. The gap between 'annoying' and 'must fix with budget' is the core risk. You need to sell to the CISO or platform engineering lead, not the individual dev. Free tier adoption won't easily convert to paid.

Technical Feasibility7/10

A solo dev can build an MVP proxy/middleware in 4-8 weeks that intercepts MCP tool calls and applies policy rules. The hard parts: supporting the explosion of CLI argument patterns (az, gh, aws all have different structures), keeping up with MCP protocol changes, and handling edge cases in command parsing. The 'last mile' of CLI subcommand parsing is deceptively complex. A basic version is feasible; a production-grade one for enterprise is 3-6 months.

Competition Gap8/10

This is the strongest dimension. Nobody is purpose-built for this. OPA is too generic. AI security companies focus on prompts, not tools. Agent frontends have primitive permission models. The specific intersection of 'fine-grained CLI/API permission control for AI agents' is genuinely unoccupied. First credible product here owns the category.

Recurring Potential8/10

Natural subscription model. Policies need ongoing management, audit logs accumulate, team seats scale. Enterprise compliance requirements create lock-in. Per-seat pricing for teams aligns value with usage. High retention once embedded in workflow.

Strengths
  • +Genuinely unoccupied niche — no purpose-built competitor exists yet
  • +Riding a massive tailwind (AI agent adoption in enterprise)
  • +Clear enterprise upgrade path with audit, SSO, and compliance features
  • +MCP is becoming a standard, making integration points well-defined
  • +Pain signal is specific, articulable, and worsening over time
Risks
  • !Anthropic/OpenAI/Cursor could ship native fine-grained permissions in a single release, killing the standalone market overnight
  • !Willingness to pay is unproven — individual devs won't pay and enterprise sales takes 6+ months
  • !CLI argument parsing across hundreds of tools is a long-tail complexity nightmare
  • !MCP protocol is still evolving — building on shifting ground
  • !Small current market means slow initial traction; you're betting on timing
Competition
Anthropic's Claude Code Built-in Permissions

Native permission system in Claude Code that allows/denies tool access at the command level

Pricing: Included with Claude Code subscription (~$20-100/mo
Gap: Only one level deep for CLI subcommands. No cross-agent policy management, no audit trail, no team-wide policy enforcement, no approval workflows. Can't express 'allow az vm list but deny az vm delete'.
Open Policy Agent (OPA) / Styra

General-purpose policy engine using Rego language. Can theoretically be wired to enforce fine-grained access control on any API or CLI call. Styra offers managed OPA with a UI.

Pricing: OPA is open-source. Styra DAS starts ~$500/mo for teams.
Gap: Not purpose-built for AI agents. Zero integration with MCP, Claude Code, Copilot, or any AI coding tool. Requires significant custom glue code. No awareness of AI agent context (prompt, intent, session).
Lasso Security / Prompt Security

AI security platforms focused on prompt injection defense, data loss prevention, and guardrails for LLM inputs/outputs. Monitor and filter what goes in and out of AI models.

Pricing: Enterprise pricing, typically $10K+/year
Gap: Focused on prompt/response layer, NOT on tool-use permissions. Don't solve the 'should this agent be allowed to run az vm delete' problem. No CLI-level granularity. No MCP integration.
Guardrails AI

Open-source framework for adding validation and guardrails to LLM outputs. Validators check if outputs meet criteria before being returned to users.

Pricing: Open-source core. Guardrails Hub is free. Enterprise tier pricing undisclosed.
Gap: Output validation only — doesn't intercept tool calls or CLI execution. No permission model, no policy engine, no audit logging. Solving a different layer of the problem.
MCP Server Implementations (community)

Various open-source MCP server wrappers on GitHub that add basic auth or scoping to MCP tool access. Examples include mcp-proxy projects and gateway patterns emerging in the ecosystem.

Pricing: Free / open-source
Gap: Fragmented, no unified product. No UI, no audit logs, no team management. No approval workflows. Hobbyist quality — not enterprise-ready. No subcommand-level granularity for CLIs.
MVP Suggestion

MCP proxy server that sits between Claude Code and MCP tool servers. Config file (YAML/JSON) where you define allow/deny rules at the subcommand level (e.g., 'az vm list: allow, az vm delete: deny'). CLI to manage policies. Local audit log of all tool calls with allow/deny decisions. Ship as a single binary or npm package. Target Claude Code users first since they have the most acute pain. Skip UI, skip teams, skip SSO — just nail the single-dev policy engine.

Monetization Path

Free open-source CLI for individual devs (build community + GitHub stars) -> Pro tier at $15/mo for advanced policies, cloud audit log dashboard, and Slack/email approval workflows -> Team tier at $30/seat/mo for centralized policy management, SSO, and compliance exports -> Enterprise at custom pricing for org-wide deployment, SOC2 audit support, and on-prem option

Time to Revenue

3-5 months. First 6-8 weeks building open-source MVP and getting community traction. Months 2-4 iterating based on feedback and adding team features. First paying customers likely month 4-5, from early adopters who hit the pain in production and need audit logs for compliance.

What people are saying
  • Most agent frontends only give you one level deep of CLI commands to authorize
  • It is absurd to grant Claude Code permission to az vm:*
  • setting granular permissions per tool
  • complex CLIs like GitHub, Azure, etc. it just doesn't scale well