RAWThink vs Shodh Memory
A side-by-side look at the RAWThink and Shodh Memory MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose RAWThink for knowledge & memory work as a local process; choose Shodh Memory for knowledge & memory as a local process. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose RAWThink when
- You need dedicated capabilities in the Knowledge & Memory domain.
- You prefer a local stdio subprocess transport.
- You want tools like
search_thoughts, get_session, store_thought.
Choose Shodh Memory when
- You need dedicated capabilities in the Knowledge & Memory domain.
- You prefer a local stdio subprocess transport.
- Its auth model fits you: No auth required.
- You want tools like
remember, recall, recall_by_tags.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Knowledge & Memory | Knowledge & Memory |
| Quality signal | 49/100 · Fair | 69/100 · Great |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | Not declared | No auth required |
| Pricing | Not declared | Free |
| Required env vars | None listed | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | 0 | 314 |
| Directory activity | 0 views 0 installs 0 upvotes | 6 views 0 installs 0 upvotes |
| Tools | 11 | 38 |
| Full listing | View RAWThink | View Shodh Memory |
Tools & capabilities
RAWThink tools 11
search_thoughtsHybrid search. `mode="overview"` gives one line per sessionget_sessionFull content of a session by IDstore_thoughtSave a quick note as a qnotereindexRe-index the vault into Qdrantsearch_nodesBounded. Filters by `domain` and `entity_type`; reports `total_matched` and `truncatedopen_nodesSpecific entities with their relationsread_graphWhole graph, paginated, with a summary moderecordEntities, relations and observations in one validated, atomic callrecord_decisionA decision with its rejected alternativesreviseMark observations superseded, link what replaced theminvalidate_observationsBelief revision without the relation link
Shodh Memory tools 38
rememberStore a memory for future recall. Use this to remember important information, decisions, user preferences, project context, or anything you want to recall later.recallSearch memories AND todos using semantic similarity. Returns both relevant memories and matching todos. Use this to find past experiences, decisions, context, or pending work. Modes: 'semantic' (vector similarity), 'associative' (graph traversal), 'temporal' (time-based retrieval), 'hybrid' (combined), 'spatial' (geo-location based), 'mission' (mission context), 'action_outcome' (reward-based learning).recall_by_tagsFind memories by tags. Returns memories matching ANY of the provided tags. Useful for finding memories by category (e.g., 'tool:Edit', 'file:src/main.rs', 'source:hook', 'error', 'session-summary').context_summaryGet a condensed summary of recent learnings, decisions, and context. Use this at the start of a session to quickly understand what you've learned before.list_memoriesList all stored memoriesforgetDelete a specific memory by IDmemory_statsGet statistics about stored memoriesverify_indexVerify vector index integrity - diagnose orphaned memories that are stored but not searchable. Returns health status and count of orphaned memories.repair_indexRepair vector index by re-indexing orphaned memories. Use this when verify_index shows unhealthy status. Returns count of repaired memories.backup_createCreate a backup of all memories. Returns backup metadata including ID, size, and checksum. Backups are stored locally and can be restored later.backup_listList all available backups for this user. Returns backup history with IDs, timestamps, and sizes.backup_verifyVerify backup integrity using SHA-256 checksum. Use to check if a backup is corrupted before restoring.- +26 more on the listing page
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
RAWThink
{
"mcpServers": {
"rawthink": {
"command": "uvx",
"args": [
"rawthink-mcp"
]
}
}
}
Shodh Memory
{
"mcpServers": {
"varun29ankus-shodh-memory": {
"command": "npx",
"args": [
"-y",
"@shodh/memory-mcp"
]
}
}
}
Frequently asked questions
RAWThink is categorized under Knowledge & Memory and uses a local stdio subprocess. Shodh Memory belongs to Knowledge & Memory and uses a local stdio subprocess. Pick RAWThink for knowledge & memory work and Shodh Memory for knowledge & memory.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.
RAWThink has no declared pricing — check the project's own site. Shodh Memory is listed as free. Auth: no auth required. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add rawthink and varun29ankus-shodh-memory as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, RAWThink has a quality signal of 49/100 (Fair) with 0 views, 0 installs and 0 GitHub stars. Shodh Memory has 69/100 (Great) with 6 views, 0 installs and 314 GitHub stars.