io.github.Dakera-AI/dakera-mcp
OCI · GHCR.IO/DAKERA-AI/DAKERA-MCP
Agent memory engine — 106 MCP tools, self-hosted, single Rust binary
Available components
Last scanned (10 hours ago)
Scores higher than 68% of OCI servers
Category Memory and Knowledge
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 Security0
- No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.Unverified
- Known CVEs could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.Unverified
- Install-script risk not yet assessed.Unverified
- Dependency health could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.Unverified
Provenance & Transparency35
- 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: no license is declared. See how to fix → Fail
- Actively maintained (last published 13 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability67
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 1823 tokens (~130/item across 14 items; 14 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage91
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 72% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 14 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 15 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities20
- Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28. See how to fix → Fail
Unverified: 1 category
A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.
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.
- 31 Oct 26 0
- Stability: 0.97 → pass security
- 30 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.
- 28 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.
- 26 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.
- 24 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 73 to 77. That category is still filling its 30-day observation window: 22 days of observed history at the previous scan, 23 at this one. The score rises as the window fills, whether or not the server changes.
- 22 Oct 26 0
- Tool safety: pass → unverified ▼ security
- Stability: 0.67 → unverified ▼ security
- Capabilities: fail → unverified ▼ functional
- Tool coverage: 100 → unverified ▼ functional
- Package version: 0.12.2 → 0.12.3 functional
- 20 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 60 to 63. That category is still filling its 30-day observation window: 18 days of observed history at the previous scan, 19 at this one. The score rises as the window fills, whether or not the server changes.
- 18 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.
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 5 Nov 2026 · Analysed oci/ghcr.io/dakera-ai/dakera-mcp@0.12.3
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | oci |
| Reason | No attestation published |
Background: How many MCP packages publish verified provenance →
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 →
dakera_batch_forget ~132
Bulk-delete memories matching filters (tags, importance range, time window, type, session); at least one is required. Permanent: to demote instead, use dakera_memory_importance.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | – |
| created_after | integer | – | After Unix timestamp |
| created_before | integer | – | Before Unix timestamp |
| max_importance | number | – | Max importance threshold |
| memory_type | string | – | – |
| min_importance | number | – | Min importance threshold |
| session_id | string | – | – |
| tags | array | – | Tags to match (all required) |
No output schema declared.
No examples provided.
dakera_batch_recall ~145
List memories by filters (tags, importance, time window, type, session) without a query; at most limit (default 100). Use instead of dakera_recall when no semantic search is needed.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | – |
| created_after | integer | – | After Unix timestamp |
| created_before | integer | – | Before Unix timestamp |
| limit | integer | – | – |
| max_importance | number | – | Max importance (inclusive) |
| memory_type | string | – | – |
| min_importance | number | – | Min importance (inclusive) |
| session_id | string | – | – |
| tags | array | – | Tags to match (all required) |
No output schema declared.
No examples provided.
dakera_discover_tools ~90
Search the Dakera tool catalog by keyword or tier (core/power/admin/meta) and return names and one-line summaries without loading full schemas. Call this first to find relevant tools, then use dakera_load_tools to fetch only the schemas you need — avoids loading the full catalog upfront.
| Name | Type | Req | Description |
|---|---|---|---|
| query | string | – | Keyword to search tool names/descriptions. |
| tier | string | – | – |
No output schema declared.
No examples provided.
dakera_extract ~155
Extract entities, topics, key phrases and a summary from text with the provider chain: extractor_override, then the namespace default, then the server default (GLiNER local). For ad-hoc GLiNER types use dakera_auto_tag. Needs a write key for the namespace (for all namespaces when neither namespace nor agent_id is given).
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | – | – |
| extractor_override | object | – | Provider for this request only |
| lang | string | – | en, de, fr, es, it, pt or nl (v0.12+) |
| namespace | string | – | Namespace whose extractor config applies (default: agent_id's) |
| text | string | yes | Text to extract information from |
No output schema declared.
No examples provided.
dakera_forget ~87
Permanently delete memories by ID or tag. Provide memory_ids for exact removal or tags to bulk-delete all memories sharing those tags. Deletion is immediate and irreversible — prefer dakera_memory_importance to suppress without deleting.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | – |
| memory_ids | array | – | Specific memory IDs to delete |
| tags | array | – | Delete memories with these tags |
No output schema declared.
No examples provided.
dakera_fulltext_search ~92
BM25 keyword search over indexed documents. Use over vector search when exact-term recall matters (error codes, IDs, names). For semantic+keyword combined use dakera_hybrid_search.
| Name | Type | Req | Description |
|---|---|---|---|
| filter | object | – | Optional metadata filter |
| namespace | string | yes | Namespace to search in |
| query | string | yes | Search query text |
| top_k | integer | – | Number of results to return |
No output schema declared.
No examples provided.
dakera_hybrid_search ~175
BM25 + vector ANN hybrid search in a single pass. Omit vector for BM25-only mode. Use for RAG when pure semantic or keyword search alone is insufficient. vector_weight: 0.0=BM25, 1.0=vector (default 0.5).
| Name | Type | Req | Description |
|---|---|---|---|
| filter | object | – | Optional metadata filter |
| include_metadata | boolean | – | – |
| include_vectors | boolean | – | – |
| namespace | string | yes | Namespace to search in |
| text | string | yes | Text query for full-text search |
| top_k | integer | – | Number of results to return |
| vector | array | – | Query embedding; omit for BM25-only. |
| vector_weight | number | – | Vector score weight 0.0–1.0; text weight = 1−value. |
No output schema declared.
No examples provided.
dakera_knowledge_graph ~105
Build a knowledge graph from a seed memory using embedding similarity. Use to explore how a concept connects to stored knowledge. For BFS traversal of an existing linked graph use dakera_graph_traverse.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | – |
| depth | integer | – | Graph traversal depth (controls candidate count) |
| memory_id | string | yes | Seed memory ID to build graph from |
| min_similarity | number | – | Minimum similarity threshold 0.0-1.0 |
No output schema declared.
No examples provided.
dakera_load_tools ~58
Fetch the full inputSchema for one or more named tools. Use after dakera_discover_tools. Returns schemas for found tools and a not_found list for unrecognized names.
| Name | Type | Req | Description |
|---|---|---|---|
| tools | array | yes | Tool names to load schemas for |
No output schema declared.
No examples provided.
dakera_recall ~257
Semantic recall: the top_k (default 5) memories closest to a query, optionally narrowed by tags, memory_type or session_id. Session neighbours go in context_memories, outside top_k. include_associated adds KG neighbours one hop away (dakera_recall_associated goes deeper). Best first: rank_score (v0.12.3+) orders them; score may rise.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | – |
| include_associated | boolean | – | Include KG-linked memories in results |
| lang | string | – | en, de, fr, es, it, pt or nl (v0.12+) |
| memory_type | string | – | – |
| min_importance | number | – | Min importance threshold |
| neighborhood_mode | string | – | Session-neighbour context: separate (listed apart, the default), inline or off |
| query | string | yes | Semantic query text |
| session_id | string | – | – |
| since | string | – | Only memories created at or after this ISO-8601 timestamp |
| tags | array | – | – |
| top_k | integer | – | Max results to return |
| until | string | – | Only memories created at or before this ISO-8601 timestamp |
No output schema declared.
No examples provided.
dakera_search ~118
Semantic search with optional tag and memory-type pre-filters. Prefer over dakera_recall when results must be constrained by tag or type alongside the semantic match.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | – |
| lang | string | – | en, de, fr, es, it, pt or nl (v0.12+) |
| memory_type | string | – | Filter by memory type |
| query | string | yes | Search query text |
| tags | array | – | Filter by tags |
| top_k | integer | – | Number of results |
No output schema declared.
No examples provided.
dakera_session_end ~69
Close a session with an optional summary. Call at run end, even on error. A session the server already ended (idle) keeps its state; your summary is then not saved.
| Name | Type | Req | Description |
|---|---|---|---|
| session_id | string | yes | Session ID to end |
| summary | string | – | Optional session summary |
No output schema declared.
No examples provided.
dakera_session_start ~90
Open a session; its session_id groups the memories you store. The server ends a session idle for 4 h by default (v0.12.2+).
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | – |
| idle_timeout_secs | integer | – | End after this many idle seconds; 0 = never (v0.12.2+) |
| metadata | object | – | Optional session metadata |
No output schema declared.
No examples provided.
dakera_store ~199
Persist a memory (fact, decision, context) for an agent. importance defaults to 0.5; use 0.8-1.0 for memories that must survive decay.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | – |
| attachment_ref | string | – | sha256:<hex> uploaded to the agent's namespace (v0.12) |
| content | string | yes | Memory content text |
| expires_at | integer | – | Expiry, Unix seconds (wins over ttl_seconds) |
| importance | number | – | Importance 0.0-1.0 |
| lang | string | – | en, de, fr, es, it, pt or nl (v0.12+) |
| memory_type | string | – | – |
| metadata | object | – | – |
| session_id | string | – | Session to associate with |
| tags | array | – | Tags for filtering |
| ttl_seconds | integer | – | Expire after N seconds |
No output schema declared.
No examples provided.
How do I install the io.github.Dakera-AI/dakera-mcp server?
io.github.Dakera-AI/dakera-mcp runs locally as a container image, launched with docker run --rm -i ghcr.io/dakera-ai/dakera-mcp:0.12.3. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.
oci · ghcr.io/dakera-ai/dakera-mcp
claude mcp add dakera-ai-dakera-mcp -- docker run --rm -i ghcr.io/dakera-ai/dakera-mcp:0.12.3
What is the io.github.Dakera-AI/dakera-mcp server?
io.github.Dakera-AI/dakera-mcp is listed in the public MCP registry as io.github.Dakera-AI/dakera-mcp. Agent memory engine, 106 MCP tools, self-hosted, single Rust binary. This page covers its container image (ghcr.io/dakera-ai/dakera-mcp).
Is the io.github.Dakera-AI/dakera-mcp server safe to use?
io.github.Dakera-AI/dakera-mcp scores 47 out of 100 on VerifyMCP. 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 io.github.Dakera-AI/dakera-mcp server expose?
io.github.Dakera-AI/dakera-mcp exposes 14 tools: dakera_store, dakera_recall, dakera_forget, dakera_batch_recall, dakera_batch_forget, and 9 more. Their descriptions and schemas cost roughly 1,772 tokens of context every time the server is loaded.
Is the io.github.Dakera-AI/dakera-mcp server still maintained?
io.github.Dakera-AI/dakera-mcp is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.