MCP SERVERA blame log for why an agent changed something — including the approaches this codebase already tried and reverted.
LABSCO SUMMARY
git blame answers who and when. This answers why, for entities git has no concept of — a column, an environment variable, a dependency bump. The tool that pays for the whole thing is prior_attempts: called before an edit, it surfaces the approach that was already tried and reverted, which is exactly the failure mode of handing a codebase to a fresh agent every session. Everything is local SQLite with no model in the path, and it only works if your agent instructions tell it to log as it goes.
A local change ledger that coding agents write to as they work. Each event records the entity that changed, the diff, the reasoning behind it and the constraint it was made under, into a SQLite file beside the code — so the why survives long after the session and the prompt that produced it are gone.
Published on PyPI as selvedge and launched over stdio as selvedge-server — with uvx the entry point differs from the package name, so it needs --from selvedge — and there is an npm wrapper published as selvedge-mcp. Data lives in a SQLite file at .selvedge/selvedge.db beside the codebase, relocatable with SELVEDGE_DB. None of it fills up unless the agent actually calls log_change as it edits, which is what the few lines the README has you add to CLAUDE.md are for.
One command — pip install selvedge
USE CASES
Blame the entity for the most recent change with its reasoning, then read its full history when one answer is not enough.
Called before editing, prior_attempts shows earlier attempts on the same entity with an inferred outcome for each.
Every event sharing a changeset id, oldest first, across whichever entities the work reached.
One call after each meaningful change stores the diff and the reasoning in the same context that produced them.
Full-text search over entity paths, diffs, reasoning and agents answers questions like what was done for billing.
Decisions past their revisit date, or whose stale condition has triggered, surface without anyone having to remember them.
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
blameMost recent change to an entity — what changed, when, who, why.
Like git blame but for semantic entities (DB columns, functions, env vars, dependencies) and AI agents. Also carries the derived decision state: status (active / reverted / reopened) and superseded_by (id of a later supersede overriding this change, or ""). If no history exists for the entity, returns {"error": "..."} with protocol-level isError: false.
changesetAll events that share a changeset_id, oldest first.
Use to reconstruct the full scope of a feature or task across multiple entities. If the changeset has no events, returns [{"error": "..."}] so the caller can distinguish "unknown changeset" from "empty history."
diffGet change history for a codebase entity, newest first.
Supports prefix matching — e.g. 'users' returns all events for the users table and any users.* column. Each event carries a derived superseded_by id ("" when nothing overrode it), so the tried → reverted → re-opened trail reads straight off the history.
historyFiltered change history across all entities, newest first.
Combine since, entity_path, project, and changeset_id to scope the result. On unparseable since input the response is [{"error": "..."}] so the caller sees the problem.
log_changeRecord a change to a codebase entity.
Call this immediately after making any meaningful change. The event is written to the local SQLite store and returned with its assigned id and timestamp. If the reasoning fails the quality validator (empty, too short, or a generic placeholder), or the entity_path doesn't match the usual shape for its entity_type, the result includes a warnings array — the event is still stored.
Renames: pass the new path in entity_path, set change_type="rename", and pass the old path in rename_from. Selvedge then writes two events — a rename on the old path and a create on the new path with metadata.renamed_from set — so the entity's history follows it. Example:
log_change( entity_path="src/auth/session.py::login", # new path change_type="rename", rename_from="src/auth.py::login", # old path entity_type="function", reasoning="Split auth.py into an auth/ package; login moved.", )
Superseding a reverted decision: when a reverted change becomes correct again (the constraint that killed it no longer holds), do NOT delete or edit history — log with change_type="supersede" and the reason. The new event links the prior revert (auto-resolved when supersedes is empty) and every read surface then reports the trail tried → reverted → re-opened. Never re-apply a reverted change without superseding it first.
On validation failure (invalid change_type, missing entity_path, rename_from set without change_type='rename', supersedes set without change_type='supersede', or a supersede with nothing to re-open) the result is {"status": "error", "error": "..."} with no event written.
prior_attemptsPrior change attempts on an entity, each with an inferred outcome.
Call this BEFORE editing an entity. If the same change was tried before and reverted, you get the prior reasoning and change_type plus an inferred outcome — so you can change your plan instead of repeating a rejected approach.
Each result is a change event plus the trail fields: outcome ("reverted" — a later removal on the path; "reopened" — reverted but a later supersede re-opened it; "active"), confidence ("proximity_high" / "proximity_low"), outcome_reasoning (WHY it was rejected), superseded_by + supersede_reasoning (the re-open, when present), and current_status — the entity's standing now. Treat "reverted" as "don't repeat this without a supersede"; "reopened" means the old revert no longer stands. Together they read: tried → reverted → re-opened. Templated and deterministic — no LLM call; pull-only.
Conservative by design — min_confidence defaults to "proximity_high", so an empty list (nothing clearly tried-and-rejected) is the normal, preferred answer over a speculative false positive. Pass min_confidence="proximity_low" to widen recall. Rows carry match_type ("exact" / "substring" / "fuzzy") and similarity.
searchFull-text search across entity paths, diffs, reasoning, and agents.
Useful for questions like 'what changes were made for the billing feature?', 'which columns were added by cursor?', or 'show everything related to authentication'.
stale_decisionsDecisions due for a revisit — past their date, or with a triggered stale condition.
Two deterministic rules. Date-based (flag="revisit_due"): events whose revisit_after has passed AND the entity is still live (queried via blame/diff/prior_attempts after the decision, or its changeset saw later activity) — pure age alone never surfaces. Condition-based (flag="review_suggested"): events whose stale_when text shares keywords with a LATER change event — the named invalidation evidence may have happened. Surfacing only: nothing is un-retired automatically; follow up with a supersede if the condition really was triggered.
Each result is the change event plus flag, revisit_due, days_overdue, active_use_signals, matched_terms, matched_event_id, and a one-line stale_reason. Date-due rows first, most-overdue leading; filter by entity_path, project, or agent. Templated and deterministic; no LLM call.
BEFORE YOU INSTALL
8 tools when we connected.
CONTEXT COST
Rated by the size of the 8 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
pip install selvedge/plugin marketplace add masondelan/selvedge
/plugin install selvedge@selvedge{
"mcpServers": {
"selvedge": {
"command": "selvedge-server"
}
}
}MCP servers
Foxfire1st
AIAppsAPI
STiFLeR7
gunning4it