pg.ddx.io: the PostgreSQL community's memory
Search PostgreSQL mailing lists, commits, commitfest and docs, each cross-linked
- Pricing
- Free
- Platforms
- API, Web
- Runs
- Remotely
- Version
- 2026.10.22
- Listing updated
- 2 days ago
About pg.ddx.io: the PostgreSQL community's memory
pg.ddx.io: the PostgreSQL community's memory is a free MCP server for databases. It runs as a hosted remote server, so there is nothing to install locally.
The archive holds 85 mailing lists and issue trackers back to 1991, 18 git repositories, the commitfest, cfbot, the buildfarm, docs for releases 14 to 19 and the wiki. Its distinguishing feature is linking: a thread lists the commits it produced, and a commit links the thread named in its Discussion line, so an agent can cite both.
A worked example on the site traces a cursor crash at temp_file_limit from the bug thread to the fix commit and the first releases that shipped it. Tools read code at any tag, branch or commit since 1996 with blame and grep, follow a patch through the commitfest and cfbot, and check buildfarm status. The default endpoint lists the core tools and /mcp/full lists all 126.
It is free, read-only and needs no account. Two optional cookies remember search settings, access logs are kept 7 days, and the site says it is run by one person as a public good. A legacy SSE endpoint exists for older clients.
Install
Run in a terminal
claude mcp add --transport http archive https://pg.ddx.io/mcpAdd to Settings → Connectors → Add custom connector
https://pg.ddx.io/mcpAdd to ~/.cursor/mcp.json
{
"mcpServers": {
"archive": {
"url": "https://pg.ddx.io/mcp"
}
}
}Add to .vscode/mcp.json
{
"servers": {
"archive": {
"type": "http",
"url": "https://pg.ddx.io/mcp"
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"archive": {
"serverUrl": "https://pg.ddx.io/mcp"
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"archive": {
"type": "http",
"url": "https://pg.ddx.io/mcp"
}
}
}Tools this server provides (11)
Taken from the project documentation; the running server may differ.
- hybrid_search
- Keyword and semantic search across the archive.
- cross_reference
- Link a thread and its commits.
- get_thread
- Fetch a mailing list thread.
- get_commit
- Commit details with first releases.
- read_file
- Read a file at any tag, branch or commit.
- blame
- Blame a file.
- code_search
- Search the code.
- search_commitfest
- Search commitfest entries.
- get_entry
- Get a commitfest entry.
- find_failing_patches
- Find patches failing in cfbot.
- commit_buildfarm_status
- Buildfarm status for a commit.
What it does
- Thread and commit linking
- Each thread lists its commits and each commit its discussion thread.
- Code at any version
- Read files, blame and grep at any tag, branch or commit since 1996.
- Commitfest tracking
- Follow patches through the commitfest, cfbot and buildfarm.
- Hybrid search
- Keyword and semantic ranking across lists, docs, wiki and commits.
- Search syntax
- Phrases, exclusions, site, date, regex and link filters.
- 126 tools
- Core set by default, full set at /mcp/full.
Good for
- Find why a PostgreSQL behavior changed and cite the thread
- See which releases first shipped a bug fix
- Check where a commitfest patch stands
- Read a function as of an old release tag
- Find failing patches in the buildfarm
Pricing
Free
Free, read-only, no account
Prices change. Check pg.ddx.io before you buy.
pg.ddx.io: the PostgreSQL community's memory FAQ
Does it need an account?
No key or account is needed.
How many tools are there?
126 in total; the default endpoint lists the core tools.
Which transports are offered?
Streamable HTTP, plus legacy SSE.
What data is kept?
Two optional cookies; access logs are kept 7 days.
Is it free?
Yes, free and read-only.
Is pg.ddx.io: the PostgreSQL community's memory free?
Yes. pg.ddx.io: the PostgreSQL community's memory is free to use.
How do I add pg.ddx.io: the PostgreSQL community's memory to Claude Code?
Run this command in your terminal: claude mcp add --transport http archive https://pg.ddx.io/mcp
What are the best alternatives to pg.ddx.io: the PostgreSQL community's memory?
The closest alternatives to pg.ddx.io: the PostgreSQL community's memory are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.
Alternatives to pg.ddx.io: the PostgreSQL community's memory

REA
MCP serverCLI and MCP server that lets coding agents reverse engineer apps and binaries
Runs locally- Open source
- 464K GitHub stars
- Developer tools

Codebase Memory
MCP serverLocal MCP server that builds a code knowledge graph for AI coding agents
Runs locally- Open source
- 48.7K GitHub stars
- Knowledge and memory

GitHub
MCP serverOfficial MCP server connecting AI assistants to GitHub repos, issues and workflows
Not checked yet- Remote
- Open source
- 34.5K GitHub stars
- Developer tools

Serena MCP: the IDE for your agent
MCP serverMCP toolkit giving coding agents symbol-level code retrieval and editing
Runs locally- Open source
- 31.5K GitHub stars
- Developer tools

XERJ
MCP serverLocal search engine for AI agents with cited answers over your code and docs
Runs locally- Open source
- 19.2K GitHub stars
- Knowledge and memory

Ouroboros
MCP serverSpec-first layer that pins requirements and verifies results of AI coding agent work
Runs locally- Open source
- 6.4K GitHub stars
- Developer tools