bonito-mcp
The killer differentiator of Bonito (BON-004): an MCP server that gives any AI agent (Claude, Bedrock, Strands) native access to deep database observability. No Datadog DB Monitoring, DBmarlin or Percona PMM expose MCP — Bonito does.
It is a thin wrapper over the bonito-api REST layer (business logic lives in
store/API, not duplicated here).
Run
uv pip install -e bonito-mcp # local (repo checkout)
pip install bonito-mcp-server # from PyPI
export BONITO_API_URL=http://localhost:8100
export BONITO_API_KEY=change-me
bonito-mcp # stdio transport
PyPI name note: the distribution is
bonito-mcp-server— the bare namebonito-mcpis already taken on PyPI by an unrelated project. The console command is stillbonito-mcp. Withuvx, useuvx --from bonito-mcp-server bonito-mcp.
Connect to an agent
Claude Desktop — claude_desktop_config.json:
{
"mcpServers": {
"bonito": {
"command": "bonito-mcp",
"env": { "BONITO_API_URL": "http://localhost:8100", "BONITO_API_KEY": "change-me" }
}
}
}
Claude CLI:
claude mcp add bonito -- bonito-mcp
Bedrock / Strands: the same server runs over stdio/SSE — wire it as a tool provider and the agent gets all 8 tools.
Tools
| Tool | What the agent asks |
|---|---|
get_slow_queries |
"which queries are slow?" |
get_active_locks |
"are there locks right now?" |
get_blocking_tree |
"who is blocking whom?" |
explain_query |
"what's the execution plan for this query?" |
get_wait_analysis |
"what are the sessions waiting on?" |
compare_to_baseline |
"is this query slower than usual?" |
suggest_remediation |
"what should I do about a lock / slow query / bloat?" |
get_db_health_summary |
"give me a health summary of the database" |
Config
| Env var | Default | Description |
|---|---|---|
BONITO_API_URL |
http://localhost:8100 |
Base URL of bonito-api |
BONITO_API_KEY |
(required) | API key matching the API's BONITO_API_KEY |
Token governance
query_text is truncated to 500 chars before returning to the LLM; no
secrets are ever included in tool output.
Metadata
Release files for bonito-mcp-server 0.2.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| bonito_mcp_server-0.2.0.tar.gz | 8.1 kB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| bonito_mcp_server-0.2.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 15.4 kB
Release files / bonito_mcp_server-0.2.0.tar.gz
| Download URL | bonito_mcp_server-0.2.0.tar.gz |
|---|---|
| Size | 8.1 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
959c1266a972644385f5accd4142e4bbf1d0ea90e7e5d846038e952dde77b15e
|
|
BLAKE2b-256 checksum How to use checksums |
4292823bc6872dec80cdb9ba26244bfc4c6652ac7540d0deb1e26e05a3278395
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.8.17
|
Release files / bonito_mcp_server-0.2.0-py3-none-any.whl
| Download URL | bonito_mcp_server-0.2.0-py3-none-any.whl |
|---|---|
| Size | 7.3 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
204ebeba6006d710527a589934f5091673b6668f7c4658b869ed13473491e5ff
|
|
BLAKE2b-256 checksum How to use checksums |
30dd44857e451fce7533e34b24e188af6be3c06aef0ccbbaef2c08085cd3ca2f
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.8.17
|
Security for bonito-mcp-server 0.2.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.