PeerDB MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PEERDB_URL | Yes | URL of the reachable PeerDB Flow REST gateway, for example http://localhost:8113. | |
| PEERDB_TOKEN | No | Bearer token for gateway authentication. | |
| PEERDB_PASSWORD | No | Password for HTTP Basic gateway authentication. Must be used together with PEERDB_USERNAME. | |
| PEERDB_USERNAME | No | Username for HTTP Basic gateway authentication. Must be used together with PEERDB_PASSWORD. | |
| PEERDB_READ_ONLY | No | Set to false to enable pipeline changes. When omitted, the application default is false. | false |
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 | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_peerdb_versionA | Check gateway connectivity and report the PeerDB version. |
| list_pipelinesA | List CDC and QRep pipelines, their peers and current states. |
| list_peersA | List available source and destination peers for pipeline configuration. |
| get_pipeline_statusB | Get pipeline state, configuration, snapshot progress and replication totals. |
| get_pipeline_errorsB | Read paginated pipeline logs; defaults to the 20 most recent errors. |
| get_pipeline_batchesB | Get recent CDC batches to inspect throughput and sync progress; not for QRep. |
| get_peer_slotsB | Inspect PostgreSQL replication slots and lag for a source peer. |
| diagnose_pipelineA | Combine status, recent errors and CDC batches with heuristic troubleshooting steps. Reports partial results if a check fails. Never repairs or changes a pipeline. |
| validate_pipelineA | Ask PeerDB to validate a CDC configuration without creating a pipeline. |
| create_pipelineB | Validate and create a CDC pipeline using existing peers. May copy source data. |
| pause_pipelineA | Request pause of a running pipeline. Poll status to observe completion. |
| resume_pipelineB | Request resume of a paused pipeline. Poll status to observe completion. |
| update_pipelineA | Modify CDC batch size, idle timeout, snapshot settings or table mappings. Requires running or paused state. Adding tables may start snapshots; removing tables stops their replication. Requests the observed state; avoid concurrent lifecycle changes. |
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 13 tools
Each tool targets a distinct action or resource: lifecycle (create/pause/resume/update), listing (pipelines/peers), status/diagnostics (status/errors/batches/slots/diagnose/validate), and version. Overlap is minimal; diagnose_pipeline is composite but clearly distinct from raw status by including heuristic troubleshooting.
All 13 tools use snake_case with a verb_noun pattern (e.g., get_peerdb_version, list_pipelines, create_pipeline). The convention is consistent throughout, with no deviations in style or case.
13 tools is well-scoped for a pipeline management server, covering connectivity, inventory, lifecycle, diagnostics, and validation. No tool appears redundant or superfluous.
Core pipeline lifecycle is covered (create, read, update, pause/resume), but there is no delete_pipeline operation to remove a pipeline. Peer management is read-only (list_peers), and QRep pipelines lack dedicated diagnostic tools (get_pipeline_batches explicitly excludes QRep). These gaps may force agents to work around missing operations.