pulsar-mcp-server
Provides an MCP server (Java/Spring Boot + Spring AI MCP starter) that exposes Apache Pulsar administrative tools (tenants/namespaces/topics/brokers/clusters/functions) and client messaging tools (produce/consume messages). Includes configuration-based feature flags and a security profile concept (read-only default, write mode via Spring profile).
Score Breakdown
⚙ Agent Friendliness
🔒 Security
README indicates a default read-only profile and a separate write mode, which is a positive least-privilege signal. However, the provided content does not document how Pulsar credentials are handled, what auth mechanism is used to connect to Pulsar, whether TLS is enforced, or how tool calls are authorized/audited—so security posture beyond the high-level read/write split is unclear. Dependency hygiene and secret handling cannot be verified from the provided data.
⚡ Reliability
Best When
You want to connect an MCP-capable agent to Pulsar in a Spring Boot application and you can enforce least-privilege (read-only by default).
Avoid When
You cannot control or constrain tool execution (especially write operations) or you need documented, fine-grained authorization and audit logs.
Use Cases
- • Building an AI agent that can manage and inspect Apache Pulsar resources
- • Allowing controlled message production/consumption via MCP tool calls
- • Automating Pulsar admin workflows (tenant/namespace/topic lifecycle) using an agent with tool-group gating
Not For
- • Running without appropriate Pulsar connectivity/credentials
- • Untrusted, high-privilege agent operation without additional guardrails
- • Use cases requiring strong auditability/approval workflows (not evidenced in provided docs)
Interface
Authentication
Authentication/authorization mechanisms to Pulsar (e.g., TLS, token providers, OAuth, admin credentials) are not described in the provided README content; only a read-only vs write operational profile is mentioned.
Pricing
Agent Metadata
Known Gotchas
- ⚠ Write-capable tool groups exist (write mode enabled by Spring profile); agents may attempt destructive actions unless tool-group flags and/or runtime profile are tightly controlled.
- ⚠ Message consumption/production semantics (ack mode, subscription handling, retries, duplicate handling) are not documented in the provided README, so agents may mishandle delivery guarantees.
- ⚠ Only a partial glimpse of tool coverage is shown; without full tool schema/docs, agents may call incorrect parameters.
Alternatives
Full Evaluation Report
Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for pulsar-mcp-server.
AI-powered analysis · PDF + markdown · Delivered within 30 minutes
Package Brief
Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.
Delivered within 10 minutes
Score Monitoring
Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.
Continuous monitoring
Scores are editorial opinions as of 2026-04-04.