RAWThink
PYPI · RAWTHINK-MCP · SCANNED SEP 20
Persistent memory for AI thinking partnerships: hybrid search and a temporal knowledge graph.
Available components
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security50
- Malware scan not yet available for this package.Unverified
- No known CVEs affecting this package version or its production dependencies.Pass
- Runs hatchling.build at install time, a recognised native-build step with no shell scripting around it. View diagnostics → Pass
- 1 of 34 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency32
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- License check failed: the license (MIT License) isn't a recognized OSI-approved license. See how to fix → Fail
- Actively maintained (last published 51 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability79
- AI-judged instruction clarity (excellent).Pass
- Tool/resource definitions use about 1752 tokens (~103/item across 17 items; 17 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management80
- Stability observed for 24 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- All 3 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
- An AI judge read all 18 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
How do I install the RAWThink MCP server?
RAWThink runs locally as a PyPI package, launched with uvx rawthink-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · rawthink-mcp
claude mcp add ygtalp-rawthink-mcp -- uvx rawthink-mcp
{
"mcpServers": {
"ygtalp-rawthink-mcp": {
"command": "uvx",
"args": [
"rawthink-mcp"
]
}
}
} {
"servers": {
"ygtalp-rawthink-mcp": {
"command": "uvx",
"args": [
"rawthink-mcp"
]
}
}
} codex mcp add ygtalp-rawthink-mcp -- uvx rawthink-mcp
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"ygtalp-rawthink-mcp": {
"type": "local",
"command": [
"uvx",
"rawthink-mcp"
],
"enabled": true
}
}
} openclaw mcp add ygtalp-rawthink-mcp --command uvx --arg rawthink-mcp
mcp_servers:
ygtalp-rawthink-mcp:
command: "uvx"
args: ["rawthink-mcp"] {
"McpServers": {
"ygtalp-rawthink-mcp": {
"Transport": "stdio",
"Command": "uvx",
"Arguments": [
"rawthink-mcp"
]
}
}
} assistant mcp add ygtalp-rawthink-mcp -t stdio -c uvx -a rawthink-mcp
{
"mcpServers": {
"ygtalp-rawthink-mcp": {
"command": "uvx",
"args": [
"rawthink-mcp"
]
}
}
} Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 20 Sept 26 −3
- Stability: pass → 0.80 functional
- 19 Sept 26 +1
- Stability: 0.97 → pass security
- 17 Sept 26 −14
- Malware scan: pass → unverified ▼ security
- 16 Sept 26 +15
- Malware scan: unverified → pass ▲ security
- 15 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.
- 14 Sept 26 −15
- Malware scan: pass → unverified ▼ security
- 13 Sept 26 −3
- Stability: pass → 0.80 functional
- 12 Sept 26 +1
- Stability: 0.97 → pass security
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 20 Sept 2026 · Analysed pypi/rawthink-mcp@2.0.1
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | pypi |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| build_backend | allowlisted | hatchling.build |
Background: Why install scripts are a supply-chain risk →
Dependencies 34 packages
| Packages resolved | 34 |
|---|---|
| Stale | 1 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
add_observations Add Observations ~43
Add new observations to existing entities in the knowledge graph.
| Name | Type | Req | Description |
|---|---|---|---|
| observations | array | yes | List of dicts with keys: entityName, contents (list of strings). |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
create_entities Create Entities ~142
Create multiple new entities in the knowledge graph. If an entity with the same name exists, new observations are merged. Each entity can have: - name (required): Entity name - entityType: Type (default "concept") - observations: List of observation strings - epistemic: "assertion" | "hypothesis" | "speculation" (optional) Observations are stored with temporal metadata (created date, status). Entities get activation tracking (activation=1.0, last_accessed=today).
| Name | Type | Req | Description |
|---|---|---|---|
| entities | array | yes | List of dicts with keys: name, entityType, observations (list of strings), epistemic (optional). |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
create_relations Create Relations ~86
Create multiple new relations between entities. Relations should be in active voice. Canonical relation types: supports, contradicts, evolved_into, depends_on, exemplifies, part_of, caused_by, enables, supersedes, related_to. Non-standard types are accepted but return a warning.
| Name | Type | Req | Description |
|---|---|---|---|
| relations | array | yes | List of dicts with keys: from, to, relationType. |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
delete_entities Delete Entities ~34
Delete multiple entities and their associated relations from the knowledge graph.
| Name | Type | Req | Description |
|---|---|---|---|
| entityNames | array | yes | List of entity names to delete. |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
delete_observations Delete Observations ~45
Delete specific observations from entities in the knowledge graph.
| Name | Type | Req | Description |
|---|---|---|---|
| deletions | array | yes | List of dicts with keys: entityName, observations (list of strings to remove). |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
delete_relations Delete Relations ~37
Delete multiple relations from the knowledge graph.
| Name | Type | Req | Description |
|---|---|---|---|
| relations | array | yes | List of dicts with keys: from, to, relationType. |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
get_session Get Session ~44
Get full content of a session by reading the markdown file directly.
| Name | Type | Req | Description |
|---|---|---|---|
| session_id | string | yes | Session identifier (e.g. "2026-03-16_001"). |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
invalidate_observations Invalidate Observations ~87
Mark observations as invalidated (belief revision tracking). Sets status='invalidated' and records invalidated_at date. Optionally records what superseded the old belief.
| Name | Type | Req | Description |
|---|---|---|---|
| entity_name | string | yes | Name of the entity whose observations to invalidate. |
| observations | array | yes | List of observation text strings to invalidate. |
| superseded_by | – | – | Optional description of what replaced these beliefs. |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
open_nodes Open Nodes ~43
Open specific nodes in the knowledge graph by their names. Returns the requested entities and all relations connected to them.
| Name | Type | Req | Description |
|---|---|---|---|
| names | array | yes | List of entity names to retrieve. |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
read_graph Read Graph ~129
Read the entire knowledge graph — all entities and relations. By default returns full entities with pagination (offset/limit). Use summary=True for a compact overview (names + types + observation counts).
| Name | Type | Req | Description |
|---|---|---|---|
| entity_type | – | – | Filter entities by type (e.g. "concept", "decision", "insight"). |
| limit | integer | – | Max entities to return (for pagination). Default 20. |
| offset | integer | – | Skip first N entities (for pagination). Default 0. |
| summary | boolean | – | If True, return compact overview. If False (default), return full entities with pagination. |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
record Record ~204
Write entities, relations and observations in one validated, atomic call. This is the single write path. Everything is validated before anything is written, so a batch that is half-valid writes nothing. Entity fields: name, entityType (required for new), domain (required for new), epistemic (assertion|hypothesis|speculation|unknown, default unknown), visibility (private|shareable, default private), observations. An observation may be a string, or {"text": ..., "kind": ...} where kind is note|decided|rejected|because|touches. Relations use the canonical vocabulary; close synonyms are folded, unknown types are rejected. A relation may only point at an entity that exists or is being created in this same call.
| Name | Type | Req | Description |
|---|---|---|---|
| entities | – | – | Entities to create or merge into. |
| observations | – | – | [{"entityName": ..., "contents": [...], "kind": ...}] |
| relations | – | – | Relations to create. |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
record_decision Record Decision ~201
Record a decision: what was chosen, what was rejected, and why. `rejected` is the field that makes this worth recording. What was chosen stays readable in the code forever; what was considered and dropped exists nowhere else, and it is the question that gets asked months later.
| Name | Type | Req | Description |
|---|---|---|---|
| because | string | yes | The constraint or reasoning that forced it. |
| decided | string | yes | What was chosen. |
| domain | string | yes | Subject area (software, music, history, ...). |
| epistemic | string | – | assertion | hypothesis | speculation | unknown. |
| name | string | yes | Stable identifier, e.g. "banking/phase-7: reference ID strategy". |
| rejected | – | – | Alternatives considered and dropped, each with its reason. |
| supersedes | – | – | Name of a decision this one replaces. |
| touches | – | – | Files or symbols this decision governs. |
| visibility | – | – | private (default) | shareable. |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
reindex Reindex ~43
Re-index vault content into the search database.
| Name | Type | Req | Description |
|---|---|---|---|
| full | boolean | – | Force full vault re-index. |
| session_id | – | – | If provided, reindex only this session. |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
revise Revise ~136
Mark observations as no longer held, and link what replaced them. Deliberately not a delete. Keeping the superseded belief, dated and linked, is what lets the archive answer "why did we change our mind" later. If you pass `superseding_entity`, record that entity first — a relation cannot point at a name the graph does not know.
| Name | Type | Req | Description |
|---|---|---|---|
| entity_name | string | yes | Entity whose observations are being revised. |
| observations | array | yes | Exact observation texts to invalidate. |
| superseded_by | – | – | Short description of what replaced them. |
| superseding_entity | – | – | Name of the entity that supersedes this one. |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
search_nodes Search Nodes ~122
Search the knowledge graph. Bounded: returns `total_matched` alongside a capped page, so a truncated result is visible rather than silent.
| Name | Type | Req | Description |
|---|---|---|---|
| domain | – | – | Narrow to one subject area (software, music, history, ...). |
| entity_type | – | – | Narrow to one role (decision, concept, finding, rule, ...). |
| limit | integer | – | Max entities returned (default 10). |
| max_relations | integer | – | Max relations returned (default 50). |
| query | string | yes | Matched against entity names, types and observations. |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
search_thoughts Search Thoughts ~127
Search vault content with hybrid semantic + keyword search.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Max results (default 10). |
| mode | string | – | "full" returns matching passages; "overview" returns one line per session (id, title, score) for orientation before drilling in. |
| query | string | yes | Natural language query (e.g. "what did I think about consciousness?"). |
| source_type | – | – | Filter by "session" or "qnote". |
| tags | – | – | Filter by tags (e.g. ["philosophy", "consciousness"]). |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
store_thought Store Thought ~93
Store a new thought — embed and save to vault as a qnote.
| Name | Type | Req | Description |
|---|---|---|---|
| session_id | – | – | Session reference linking this qnote to its source conversation. Recommended — pass the current or most recent session ID (e.g. from handoff) so qnotes can be traced back to their session context. |
| tags | – | – | Optional tags for the note. |
| text | string | yes | The thought text to store. |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
What is the RAWThink MCP server?
RAWThink is an MCP server listed in the public MCP registry as io.github.ygtalp/rawthink-mcp. Persistent memory for AI thinking partnerships: hybrid search and a temporal knowledge graph. This page covers its PyPI package (rawthink-mcp).
Is the RAWThink MCP server safe to use?
RAWThink scores 65 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the RAWThink MCP server expose?
RAWThink exposes 17 tools: search_thoughts, get_session, store_thought, reindex, search_nodes, and 12 more. Their descriptions and schemas cost roughly 1,616 tokens of context every time the server is loaded.
Is the RAWThink MCP server still maintained?
RAWThink is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.