FactoGraph
REMOTE · API.FACTOGRAPH.APP · 2 COMPONENTS
Memory for AI agents: facts a person approved, each with a link, and answers that cite them.
Available components
Last scanned (21 hours ago)
Scores higher than 53% of remote servers
Reachable. Last reached 4 Nov 2026.
Category Memory and Knowledge
Recent critical change
Authorization (22 Oct 2026). See the changelog before you install this server.
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security57
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (startStep). See how to fix → View diagnostics → Fail
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability60
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 1797 tokens (~256/item across 7 items; 7 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 Management47
- Stability observed for 14 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage98
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 93% 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 7 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 8 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
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.
- 4 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.
- 1 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.
- 30 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 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 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 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 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 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 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.
- 22 Oct 26 −7
- Authorization: partial → fail ▼ critical
- The server rewrote its instructions, which are the text every model session reads security
- New tool “startStep”, which the server declares destructive security
- Tool “createStore” rewrote its description, which is the text the model reads security
- Tool “getManual” rewrote its description, which is the text the model reads security
- Tool “listFacts” rewrote its description, which is the text the model reads security
- Tool “replyToPrompt” is now declared destructive security
- Tool coverage: 100% → 93% ▼ functional
- Schema quality: 219 → 256 ▼ functional
- Stability: unverified → 0.03 ▲ functional
- “ask” reworded the description of “store” cosmetic
- “getManual” reworded the description of “store” cosmetic
- “getStep” reworded the description of “store” cosmetic
- “listFacts” reworded the description of “store” cosmetic
- “replyToPrompt” reworded the description of “store” cosmetic
- Tool “ask” changed its title: Ask a public store → Ask a store cosmetic
- Tool “getManual” changed its title: Read a public store's manual → Read a store's manual cosmetic
- 21 Oct 26 69
First indexed and scored.
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 4 Nov 2026 · Probed https://api.factograph.app/api/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=api.factograph.app | CN=Amazon RSA 2048 M01,O=Amazon,C=US | 24 Sept 2026 | 9 Apr 2027 | RSA 2048 | SHA256-RSA | 8d15155fc6bd6652c2304fba3fc9422 |
| SANs: api.factograph.app | ||||||
| CN=Amazon RSA 2048 M01,O=Amazon,C=US (CA) | CN=Amazon Root CA 1,O=Amazon,C=US | 23 Aug 2022 | 23 Aug 2030 | RSA 2048 | SHA256-RSA | 77312380b9d6688a33b1ed9bf9ccda68e0e0f |
| CN=Amazon Root CA 1,O=Amazon,C=US (CA) | CN=Starfield Services Root Certificate Authority - G2,O=Starfield Technologies\, Inc.,L=Scottsdale,ST=Arizona,C=US | 25 May 2015 | 31 Dec 2037 | RSA 2048 | SHA256-RSA | 67f944a2a27cdf3fac2ae2b01f908eeb9c4c6 |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of api.factograph.app. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| app. | present | 23684 | 8 | Verified |
| factograph.app. | absent | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
| Header | Value |
|---|---|
| referrer-policy | no-referrer |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://api.factograph.app/api/mcp | Verified | 200 | |
| http (plaintext) | http://api.factograph.app/api/mcp | HTTPS enforced | 301 | https://api.factograph.app/api/mcp |
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 →
ask Ask a store ~180
Ask a question; the store answers only from its facts, each claim linked to its fact, and checks the answer against them. Stores nothing. Returns the step's state: `waiting` (a prompt to do and answer with replyToPrompt), `running` (call getStep), `done` (do what `next` says) or `failed`.
| Name | Type | Req | Description |
|---|---|---|---|
| question | string | yes | The person's question. |
| store | string | – | The store's link, as the person gave it: a public link (https://.../api/p/<id> or https://.../#/public/<id>, or its public id) or the person's private link (https://.../api/k/<id> or https://.../#/st… |
No output schema declared.
No examples provided.
createStore Make a store for the person ~99
A new, empty FactoGraph store of the person's own: its private link, which these tools take as `store`. Only after the person said yes to having one. Nothing is stored until the link is first opened. The link is the store's key: give it to them once, and never put it anywhere public.
| Name | Type | Req | Description |
|---|---|---|---|
| person_agreed | boolean | yes | true: the person asked for a store, or said yes when you offered one. |
No output schema declared.
No examples provided.
getManual Read a store's manual ~139
The store's manual - how to run its steps and cite its facts - and what it holds: how many facts, from which sources. Read it before the store's other tools, and follow it.
| Name | Type | Req | Description |
|---|---|---|---|
| store | string | – | The store's link, as the person gave it: a public link (https://.../api/p/<id> or https://.../#/public/<id>, or its public id) or the person's private link (https://.../api/k/<id> or https://.../#/st… |
No output schema declared.
No examples provided.
getStep Follow a step ~126
Where a running step is now: its next prompt, or its result.
| Name | Type | Req | Description |
|---|---|---|---|
| run_id | string | yes | The step's run_id. |
| store | string | – | The store's link, as the person gave it: a public link (https://.../api/p/<id> or https://.../#/public/<id>, or its public id) or the person's private link (https://.../api/k/<id> or https://.../#/st… |
No output schema declared.
No examples provided.
listFacts List every fact ~132
Every fact in the store, numbered, each number a link to the fact. Cite a fact as its number with its link, [F3](<link>).
| Name | Type | Req | Description |
|---|---|---|---|
| store | string | – | The store's link, as the person gave it: a public link (https://.../api/p/<id> or https://.../#/public/<id>, or its public id) or the person's private link (https://.../api/k/<id> or https://.../#/st… |
No output schema declared.
No examples provided.
replyToPrompt Answer a step's prompt ~191
Answer the prompt a step is waiting on - do the model work in its `system` and `messages` first. Keep answering until the step is done or failed.
| Name | Type | Req | Description |
|---|---|---|---|
| call_id | string | yes | The prompt's call_id. |
| reply | string | yes | Your answer: the JSON object the reply_schema asks for, written as JSON text - or plain text when there is no schema. |
| run_id | string | yes | The step's run_id. |
| store | string | – | The store's link, as the person gave it: a public link (https://.../api/p/<id> or https://.../#/public/<id>, or its public id) or the person's private link (https://.../api/k/<id> or https://.../#/st… |
No output schema declared.
No examples provided.
startStep Start a step in the person's store ~176
Start a step - propose, add, documents, ask or remove - in a private store, with its JSON body, as the manual says. propose stores nothing; add stores only facts the person approved, with propose's proposal_id and their reply as confirmation; remove deletes only with confirm true, after the person confirmed. Returns the step's state: `waiting` (a prompt to do and answer with replyToPrompt), `running` (call getStep), `done` (do what `next` says) or `failed`.
| Name | Type | Req | Description |
|---|---|---|---|
| body | object | yes | – |
| step | string | yes | The step to run. |
| store | string | yes | The person's private store link, as they gave it: https://.../api/k/<id> or https://.../#/store/<id>. Public links are read-only. |
No output schema declared.
No examples provided.
How do I install the FactoGraph MCP server?
FactoGraph is a hosted endpoint at https://api.factograph.app/api/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · api.factograph.app
claude mcp add --transport http app-factograph-factograph 'https://api.factograph.app/api/mcp'
What is the FactoGraph MCP server?
FactoGraph is an MCP server listed in the public MCP registry as app.factograph/factograph. Memory for AI agents: facts a person approved, each with a link, and answers that cite them. This page covers its hosted endpoint (https://api.factograph.app/api/mcp).
Is the FactoGraph MCP server safe to use?
FactoGraph scores 68 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 FactoGraph MCP server expose?
FactoGraph exposes 7 tools: getManual, listFacts, ask, startStep, getStep, and 2 more. Their descriptions and schemas cost roughly 1,043 tokens of context every time the server is loaded.
Does the FactoGraph MCP server require authentication?
No. We connected to FactoGraph without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the FactoGraph MCP server still maintained?
FactoGraph is still listed as active in the MCP registry. We last reached this channel on 4 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.