NervaPack

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/ramdhavepreetam-nervapack

About

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools

12 read · 4 write · 1 delete · 5 not yet classified

Secrets

None asked for

Install scripts

Not scanned yet

Runs as

Python package

Tools (22)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

• explore

  List entities (classes, functions, imports) in the knowledge graph. Useful for exploring what NervaPack has indexed — e.g. all classes, all functions in a specific file, or all markdown docs. Args: entity_type: Filter by type — "class", "function", "import", "markdown", or "file". Leave empty to list all. file_path: Filter to a specific file (partial match, e.g. "cli.py"). Leave empty to list across all files.

• graph_status

  Return the current state of the NervaPack knowledge graph. Shows total node and edge counts broken down by type, which languages are present, and whether any files have been modified since the last ingest (i.e., whether `nervapack sync .` needs to be run). Use this to check if the graph is stale before relying on query results.

• impact

  Perform impact analysis (reverse dependency search). Finds what depends on a given entity (e.g. who calls a function, who imports a file or class) by traversing the graph backwards. Args: target: Name of the entity (e.g. "my_function", "UserAuth", "auth.py"). max_hops: How many hops backwards to traverse (default 1).

• memory_about

  Return all current memories linked to a named entity. Args: entity: Entity name (case-insensitive, supports CamelCase → snake_case).

• memory_clear_session

  Tombstone or hard-purge all nodes belonging to a session. Args: session_id: The session node ID to clear. purge: If True, hard-delete. Default: tombstone.

• memory_end_session

  Close the current session with an outcome summary and queue consolidation. Args: summary: One-paragraph summary of what was done in this session.

• memory_for_code

  Return memories that TOUCH a given source file, optionally at a specific line. Args: file_path: Relative path to the source file (e.g. 'src/auth.py'). line: Optional line number to narrow results to overlapping ranges.

• memory_forget

  Tombstone (soft-delete) or hard-purge memory nodes. Args: node_id: Specific node ID to forget. entity: Entity name — forget all nodes linked to this entity. before: ISO timestamp — forget all nodes recorded before this date. purge: If True, hard-delete (irreversible). Default: tombstone.

• memory_import

  Bulk-seed memory from a list of node specs. Each spec: {content, kind, confidence?, entities?, rationale?, alternatives_rejected?} Args: nodes: List of node specification dicts.

• memory_list_sessions

  List all sessions with node counts, newest first. Args: limit: Maximum number of sessions to return.

• memory_recall

  Retrieve the most relevant memories for a query within a token budget. Args: query: Natural-language description of what to look for. budget_tokens: Hard token cap on the returned context block. kinds: Filter to specific node kinds (fact, decision, procedure, etc.). as_of: ISO timestamp or commit hash — retrieve memories as they were then. hops: Graph expansion hops (0–2). min_confidence: Exclude nodes below this confidence threshold. namespace: Read from this namespace without switching the active one.

• memory_start_session

  Open a named session. Returns the session ID and whether it was newly created. Args: name: Human-readable session name (e.g. "JWT auth refactor"). namespace: Switch to this namespace before opening the session.

• memory_stats

  Return node counts by kind, DB size, top entities by degree, and all namespaces. Args: namespace: If provided, show stats for this namespace instead of the active one.

• memory_store

  Persist a new memory node. Args: content: The core knowledge to store. kind: One of fact, decision, procedure, preference, outcome, action. entities: Code entity names to link via ABOUT edges (auto-created if not found). confidence: How confident this memory is (0.0–1.0). rationale: Why this decision was made (stored in data, surfaced by memory_why). alternatives_rejected: Options that were considered and rejected. touches: File paths this memory directly relates to (TOUCHES edges).

• memory_switch_namespace

  Switch the active namespace. Resets the active session. Args: namespace: Target namespace name.

Signals

Stars

1

Forks

0

Open issues

0

Weekly downloads

31

Last commit

Oct 5, 2026 (24 days ago)

Last release

Aug 5, 2026 (2 months ago)

Last package publish

Oct 5, 2026 (24 days ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Registry name

io.github.ramdhavepreetam/nervapack

Version

0.5.8

Auth

No auth

Packages

pypi nervapack

License

MIT

Repository

github.com/ramdhavepreetam/NervaPack

First seen

Oct 24, 2026

Last checked

Oct 24, 2026

Source

Official MCP Registrygithub-graphql